diff --git a/sensitivity_markers/explicit/aat_explicit.csv b/sensitivity_markers/explicit/aat_explicit.csv new file mode 100644 index 0000000..c47fb79 --- /dev/null +++ b/sensitivity_markers/explicit/aat_explicit.csv @@ -0,0 +1,124 @@ +,resource,lang,lemma,entity_id,explicit_marker,value,level +0,aat,en,immigrant,300443480,termKind,"['Pejorative', 'Deprecated']",2 +1,aat,en,indian,300310567,historicFlag,,1 +2,aat,en,indian,300016954,historicFlag,,2 +3,aat,en,indian,300016954,termKind,['AvoidUse'],2 +4,aat,en,indian,300017557,historicFlag,,1 +5,aat,en,indian,300017559,historicFlag,,1 +6,aat,en,indian,300389906,historicFlag,,1 +7,aat,en,indian,300011154,termKind,['JargonOrSlang'],1 +8,aat,en,indian,300013641,historicFlag,,1 +9,aat,en,indian,300017437,historicFlag,,3 +10,aat,en,indian,300017437,termKind,['AvoidUse'],3 +11,aat,en,indian,300013055,historicFlag,,1 +12,aat,en,homo,300310690,termKind,['JargonOrSlang'],2 +13,aat,en,hottentot,300016575,historicFlag,,3 +14,aat,en,white,300261258,historicFlag,,1 +15,aat,en,white,300250103,termKind,['JargonOrSlang'],1 +16,aat,en,white,300310656,termKind,['JargonOrSlang'],1 +17,aat,en,white,300404195,historicFlag,,1 +18,aat,en,white,300380504,historicFlag,,1 +19,aat,en,white,300264417,historicFlag,,1 +20,aat,en,white,300013647,historicFlag,,1 +21,aat,en,white,300310312,historicFlag,,1 +22,aat,en,white,300013788,historicFlag,,1 +23,aat,en,white,300012673,historicFlag,,1 +24,aat,en,white,300343778,historicFlag,,1 +25,aat,en,white,300390895,historicFlag,,1 +26,aat,en,descent,300016575,historicFlag,,3 +27,aat,en,mongoloid,300017437,historicFlag,,3 +28,aat,en,mongoloid,300017437,termKind,['AvoidUse'],3 +29,aat,en,mongoloid,300389818,termKind,['Deprecated'],2 +30,aat,en,pygmy,300310411,historicFlag,,2 +31,aat,en,pygmy,300310577,termKind,['JargonOrSlang'],1 +32,aat,en,second world,300265774,historicFlag,,2 +33,aat,en,native,300343602,historicFlag,,1 +34,aat,en,native,300400499,historicFlag,,1 +35,aat,en,native,300393173,historicFlag,,1 +36,aat,en,native,300389906,historicFlag,,1 +37,aat,en,native,300389908,historicFlag,,1 +38,aat,en,native,300389683,historicFlag,,1 +39,aat,en,native,300389684,historicFlag,,1 +40,aat,en,native,300343716,historicFlag,,1 +41,aat,en,native,300374834,historicFlag,,1 +42,aat,en,native,300375344,historicFlag,,1 +43,aat,en,native,300343680,historicFlag,,1 +44,aat,en,native,300375682,termKind,['JargonOrSlang'],1 +45,aat,en,native,300017455,termKind,['Pejorative'],3 +46,aat,en,native,300016954,historicFlag,,2 +47,aat,en,native,300016954,termKind,['AvoidUse'],2 +48,aat,en,native,300386447,historicFlag,,1 +49,aat,en,native,300266236,historicFlag,,1 +50,aat,en,native,300250608,termKind,['JargonOrSlang'],1 +51,aat,en,native,300374823,historicFlag,,1 +52,aat,en,native,300017437,historicFlag,,3 +53,aat,en,native,300017437,termKind,['AvoidUse'],3 +54,aat,en,native,300310577,termKind,['JargonOrSlang'],1 +55,aat,en,native,300343718,historicFlag,,1 +56,aat,en,native,300343721,historicFlag,,1 +57,aat,en,native,300389818,termKind,['Deprecated'],2 +58,aat,en,native,300017557,historicFlag,,1 +59,aat,en,native,300017559,historicFlag,,1 +60,aat,en,native,300343778,historicFlag,,1 +61,aat,en,native,300056500,historicFlag,,3 +62,aat,en,native,300056500,termKind,['Pejorative'],3 +63,aat,en,berber,300443574,historicFlag,,1 +64,aat,en,roots,300343602,historicFlag,,1 +65,aat,en,roots,300265699,historicFlag,,1 +66,aat,en,western,300389906,historicFlag,,1 +67,aat,en,western,300343680,historicFlag,,1 +68,aat,en,western,300310373,historicFlag,,1 +69,aat,en,western,300021930,historicFlag,,1 +70,aat,en,western,300016566,historicFlag,,1 +71,aat,en,western,300264400,historicFlag,,1 +72,aat,en,western,300343721,historicFlag,,1 +73,aat,en,western,300013561,historicFlag,,1 +74,aat,en,western,300069057,historicFlag,,1 +75,aat,en,western,300012673,historicFlag,,1 +76,aat,en,western,300106854,historicFlag,,1 +77,aat,en,western,300343778,historicFlag,,1 +78,aat,en,aboriginal,300312155,historicFlag,,1 +79,aat,en,eskimo,300017437,historicFlag,,3 +80,aat,en,eskimo,300017437,termKind,['AvoidUse'],3 +81,aat,en,eskimo,300389818,termKind,['Deprecated'],2 +82,aat,en,eskimo,300017455,termKind,['Pejorative'],3 +83,aat,en,hermaphrodite,300386060,termKind,['Deprecated'],3 +84,aat,en,indo,300386794,historicFlag,,3 +85,aat,en,oriental,300410382,historicFlag,,1 +86,aat,en,oriental,300022022,historicFlag,,2 +87,aat,en,oriental,300041759,historicFlag,,1 +88,aat,en,oriental,300041759,termKind,['JargonOrSlang'],1 +89,aat,en,colored,300252337,termKind,['JargonOrSlang'],1 +90,aat,en,colored,300310552,historicFlag,,1 +91,aat,en,colored,300013788,historicFlag,,1 +92,aat,en,inuit,300017455,termKind,['Pejorative'],3 +93,aat,en,black,300261258,historicFlag,,1 +94,aat,en,black,300375682,termKind,['JargonOrSlang'],1 +95,aat,en,black,300310656,termKind,['JargonOrSlang'],1 +96,aat,en,black,300400883,historicFlag,,1 +97,aat,en,black,300013568,historicFlag,,1 +98,aat,en,dwarf,300310411,historicFlag,,2 +99,aat,en,dwarf,300310690,termKind,['JargonOrSlang'],2 +100,aat,en,race,300000597,historicFlag,,1 +101,aat,en,primitive,300069057,historicFlag,,1 +102,aat,en,primitive,300310154,historicFlag,,1 +103,aat,en,primitive,300056500,historicFlag,,3 +104,aat,en,primitive,300056500,termKind,['Pejorative'],3 +105,aat,en,slave,300230899,termKind,['Pejorative'],3 +106,aat,en,slave,300055309,historicFlag,,2 +107,aat,en,primitivism,300056500,historicFlag,,3 +108,aat,en,primitivism,300056500,termKind,['Pejorative'],3 +109,aat,en,indigenous,300387760,historicFlag,,1 +110,aat,en,indigenous,300017437,historicFlag,,3 +111,aat,en,indigenous,300017437,termKind,['AvoidUse'],3 +112,aat,en,indigenous,300389818,termKind,['Deprecated'],2 +113,aat,en,indigenous,300264462,historicFlag,,1 +114,aat,en,indigenous,300056500,historicFlag,,3 +115,aat,en,indigenous,300056500,termKind,['Pejorative'],3 +116,aat,en,traditional,300021946,historicFlag,,1 +117,aat,en,traditional,300021930,historicFlag,,1 +118,aat,en,traditional,300264462,historicFlag,,1 +119,aat,en,traditional,300106840,historicFlag,,1 +120,aat,en,tribe,300438481,termKind,['JargonOrSlang'],1 +121,aat,en,tribe,300017557,historicFlag,,1 +122,aat,en,tribe,300017559,historicFlag,,1 diff --git a/sensitivity_markers/explicit/aat_explicit_queries.txt b/sensitivity_markers/explicit/aat_explicit_SPARQL.txt similarity index 57% rename from sensitivity_markers/explicit/aat_explicit_queries.txt rename to sensitivity_markers/explicit/aat_explicit_SPARQL.txt index 8afdbed..03e1b8e 100644 --- a/sensitivity_markers/explicit/aat_explicit_queries.txt +++ b/sensitivity_markers/explicit/aat_explicit_SPARQL.txt @@ -1,25 +1,29 @@ -aat historic flag +# historic flag SELECT DISTINCT ?concept -WHERE { +WHERE { VALUES ?lang {aat:300388277 aat:300388256} ?concept skos:inScheme aat: ; xl:prefLabel|xl:altLabel ?label. -?label gvp:historicFlag ?flag . +?label gvp:historicFlag ?flag ; + dcterms:language ?lang . } +# term Kind + SELECT DISTINCT ?concept ?flag -WHERE { +WHERE { VALUES ?lang {aat:300388277 aat:300388256} ?concept skos:inScheme aat: ; xl:prefLabel|xl:altLabel ?label. -?label gvp:termKind ?flag . +?label gvp:termKind ?flag ; + dcterms:language ?lang . FILTER (regex(str(?flag), "AvoidUse") || regex(str(?flag), "Pejorative") || regex(str(?flag), "Deprecated") || regex(str(?flag), "JargonOrSlang")) - -} \ No newline at end of file + + } \ No newline at end of file diff --git a/sensitivity_markers/explicit/aat_historicFlag_all.csv b/sensitivity_markers/explicit/aat_historicFlag_all.csv index 12279d3..c112689 100644 --- a/sensitivity_markers/explicit/aat_historicFlag_all.csv +++ b/sensitivity_markers/explicit/aat_historicFlag_all.csv @@ -1,237 +1,199 @@ concept +http://vocab.getty.edu/aat/300056500 http://vocab.getty.edu/aat/300451373 -http://vocab.getty.edu/aat/300310701 -http://vocab.getty.edu/aat/300300034 -http://vocab.getty.edu/aat/300448861 -http://vocab.getty.edu/aat/300451364 -http://vocab.getty.edu/aat/300451384 -http://vocab.getty.edu/aat/300448859 -http://vocab.getty.edu/aat/300451386 -http://vocab.getty.edu/aat/300448906 -http://vocab.getty.edu/aat/300021930 http://vocab.getty.edu/aat/300451376 -http://vocab.getty.edu/aat/300451371 -http://vocab.getty.edu/aat/300451370 http://vocab.getty.edu/aat/300451377 +http://vocab.getty.edu/aat/300451384 +http://vocab.getty.edu/aat/300451386 +http://vocab.getty.edu/aat/300448859 +http://vocab.getty.edu/aat/300448861 +http://vocab.getty.edu/aat/300448863 http://vocab.getty.edu/aat/300448879 +http://vocab.getty.edu/aat/300451364 http://vocab.getty.edu/aat/300451366 http://vocab.getty.edu/aat/300451368 http://vocab.getty.edu/aat/300451369 -http://vocab.getty.edu/aat/300448863 -http://vocab.getty.edu/aat/300007590 -http://vocab.getty.edu/aat/300013967 -http://vocab.getty.edu/aat/300056500 +http://vocab.getty.edu/aat/300451370 +http://vocab.getty.edu/aat/300451371 +http://vocab.getty.edu/aat/300448906 http://vocab.getty.edu/aat/300443574 http://vocab.getty.edu/aat/300388663 -http://vocab.getty.edu/aat/300443484 -http://vocab.getty.edu/aat/300451360 -http://vocab.getty.edu/aat/300435324 -http://vocab.getty.edu/aat/300161848 -http://vocab.getty.edu/aat/300417310 -http://vocab.getty.edu/aat/300410382 -http://vocab.getty.edu/aat/300400878 +http://vocab.getty.edu/aat/300007590 http://vocab.getty.edu/aat/300400499 -http://vocab.getty.edu/aat/300393173 -http://vocab.getty.edu/aat/300389683 -http://vocab.getty.edu/aat/300389684 -http://vocab.getty.edu/aat/300387783 -http://vocab.getty.edu/aat/300389906 -http://vocab.getty.edu/aat/300389908 -http://vocab.getty.edu/aat/300343716 -http://vocab.getty.edu/aat/300343803 -http://vocab.getty.edu/aat/300343680 -http://vocab.getty.edu/aat/300343710 -http://vocab.getty.edu/aat/300375009 -http://vocab.getty.edu/aat/300374834 -http://vocab.getty.edu/aat/300375344 -http://vocab.getty.edu/aat/300387760 -http://vocab.getty.edu/aat/300343602 -http://vocab.getty.edu/aat/300310567 -http://vocab.getty.edu/aat/300261258 -http://vocab.getty.edu/aat/300404810 -http://vocab.getty.edu/aat/300310682 -http://vocab.getty.edu/aat/300379745 -http://vocab.getty.edu/aat/300310373 -http://vocab.getty.edu/aat/300311575 -http://vocab.getty.edu/aat/300264540 -http://vocab.getty.edu/aat/300310411 -http://vocab.getty.edu/aat/300205002 -http://vocab.getty.edu/aat/300053443 -http://vocab.getty.edu/aat/300128222 -http://vocab.getty.edu/aat/300310700 -http://vocab.getty.edu/aat/300006733 -http://vocab.getty.edu/aat/300053581 -http://vocab.getty.edu/aat/300210422 -http://vocab.getty.edu/aat/300258669 -http://vocab.getty.edu/aat/300022453 -http://vocab.getty.edu/aat/300107466 -http://vocab.getty.edu/aat/300021931 -http://vocab.getty.edu/aat/300021946 -http://vocab.getty.edu/aat/300016954 -http://vocab.getty.edu/aat/300014918 -http://vocab.getty.edu/aat/300015033 -http://vocab.getty.edu/aat/300013240 -http://vocab.getty.edu/aat/300013305 +http://vocab.getty.edu/aat/300055732 +http://vocab.getty.edu/aat/300400490 +http://vocab.getty.edu/aat/300041363 http://vocab.getty.edu/aat/300013342 -http://vocab.getty.edu/aat/300312239 -http://vocab.getty.edu/aat/300004364 -http://vocab.getty.edu/aat/300000597 +http://vocab.getty.edu/aat/300386794 +http://vocab.getty.edu/aat/300380504 +http://vocab.getty.edu/aat/300012673 +http://vocab.getty.edu/aat/300013641 +http://vocab.getty.edu/aat/300310312 +http://vocab.getty.edu/aat/300250055 +http://vocab.getty.edu/aat/300075947 +http://vocab.getty.edu/aat/300310567 +http://vocab.getty.edu/aat/300312155 +http://vocab.getty.edu/aat/300002691 +http://vocab.getty.edu/aat/300263133 +http://vocab.getty.edu/aat/300310107 +http://vocab.getty.edu/aat/300263134 +http://vocab.getty.edu/aat/300041759 http://vocab.getty.edu/aat/300265675 -http://vocab.getty.edu/aat/300022022 -http://vocab.getty.edu/aat/300375386 -http://vocab.getty.edu/aat/300386447 -http://vocab.getty.edu/aat/300374862 -http://vocab.getty.edu/aat/300374881 -http://vocab.getty.edu/aat/300310552 -http://vocab.getty.edu/aat/300386478 -http://vocab.getty.edu/aat/300310702 -http://vocab.getty.edu/aat/300389914 -http://vocab.getty.edu/aat/300249973 -http://vocab.getty.edu/aat/300039221 -http://vocab.getty.edu/aat/300393188 -http://vocab.getty.edu/aat/300266236 -http://vocab.getty.edu/aat/300256706 -http://vocab.getty.edu/aat/300212527 -http://vocab.getty.edu/aat/300264467 -http://vocab.getty.edu/aat/300191611 -http://vocab.getty.edu/aat/300264501 -http://vocab.getty.edu/aat/300189864 -http://vocab.getty.edu/aat/300022552 -http://vocab.getty.edu/aat/300310153 -http://vocab.getty.edu/aat/300395589 -http://vocab.getty.edu/aat/300311325 -http://vocab.getty.edu/aat/300053852 -http://vocab.getty.edu/aat/300021444 +http://vocab.getty.edu/aat/300343778 +http://vocab.getty.edu/aat/300263583 +http://vocab.getty.edu/aat/300435324 http://vocab.getty.edu/aat/300016575 -http://vocab.getty.edu/aat/300404195 -http://vocab.getty.edu/aat/300012909 -http://vocab.getty.edu/aat/300005766 -http://vocab.getty.edu/aat/300005378 -http://vocab.getty.edu/aat/300000905 -http://vocab.getty.edu/aat/300266755 -http://vocab.getty.edu/aat/300312367 -http://vocab.getty.edu/aat/300310676 -http://vocab.getty.edu/aat/300013445 +http://vocab.getty.edu/aat/300016954 +http://vocab.getty.edu/aat/300056550 http://vocab.getty.edu/aat/300400883 -http://vocab.getty.edu/aat/300013574 -http://vocab.getty.edu/aat/300015529 -http://vocab.getty.edu/aat/300016566 -http://vocab.getty.edu/aat/300021932 +http://vocab.getty.edu/aat/300310552 +http://vocab.getty.edu/aat/300013293 +http://vocab.getty.edu/aat/300012909 +http://vocab.getty.edu/aat/300013568 +http://vocab.getty.edu/aat/300013240 +http://vocab.getty.edu/aat/300013647 +http://vocab.getty.edu/aat/300258669 http://vocab.getty.edu/aat/300265156 -http://vocab.getty.edu/aat/300300970 -http://vocab.getty.edu/aat/300003762 -http://vocab.getty.edu/aat/300134560 -http://vocab.getty.edu/aat/300212893 -http://vocab.getty.edu/aat/300380504 -http://vocab.getty.edu/aat/300400490 -http://vocab.getty.edu/aat/300258325 -http://vocab.getty.edu/aat/300310107 -http://vocab.getty.edu/aat/300419330 -http://vocab.getty.edu/aat/300343672 -http://vocab.getty.edu/aat/300343893 -http://vocab.getty.edu/aat/300374823 -http://vocab.getty.edu/aat/300374956 -http://vocab.getty.edu/aat/300343828 -http://vocab.getty.edu/aat/300004590 -http://vocab.getty.edu/aat/300007466 +http://vocab.getty.edu/aat/300004364 +http://vocab.getty.edu/aat/300343479 +http://vocab.getty.edu/aat/300013499 http://vocab.getty.edu/aat/300011337 -http://vocab.getty.edu/aat/300263583 -http://vocab.getty.edu/aat/300013834 -http://vocab.getty.edu/aat/300013641 -http://vocab.getty.edu/aat/300014532 -http://vocab.getty.edu/aat/300017437 -http://vocab.getty.edu/aat/300053463 -http://vocab.getty.edu/aat/300075947 +http://vocab.getty.edu/aat/300004590 http://vocab.getty.edu/aat/300264085 -http://vocab.getty.edu/aat/300264396 -http://vocab.getty.edu/aat/300041759 -http://vocab.getty.edu/aat/300298984 -http://vocab.getty.edu/aat/300312147 -http://vocab.getty.edu/aat/300216057 -http://vocab.getty.edu/aat/300419983 -http://vocab.getty.edu/aat/300343718 http://vocab.getty.edu/aat/300006460 -http://vocab.getty.edu/aat/300249920 -http://vocab.getty.edu/aat/300013910 -http://vocab.getty.edu/aat/300024422 -http://vocab.getty.edu/aat/300264509 -http://vocab.getty.edu/aat/300264417 -http://vocab.getty.edu/aat/300005246 -http://vocab.getty.edu/aat/300400658 -http://vocab.getty.edu/aat/300039007 -http://vocab.getty.edu/aat/300037592 -http://vocab.getty.edu/aat/300312362 -http://vocab.getty.edu/aat/300265682 -http://vocab.getty.edu/aat/300264400 -http://vocab.getty.edu/aat/300379254 -http://vocab.getty.edu/aat/300343721 -http://vocab.getty.edu/aat/300013438 -http://vocab.getty.edu/aat/300013647 -http://vocab.getty.edu/aat/300012929 -http://vocab.getty.edu/aat/300021916 -http://vocab.getty.edu/aat/300197148 +http://vocab.getty.edu/aat/300013561 +http://vocab.getty.edu/aat/300006733 +http://vocab.getty.edu/aat/300015529 +http://vocab.getty.edu/aat/300028749 +http://vocab.getty.edu/aat/300015638 +http://vocab.getty.edu/aat/300022453 +http://vocab.getty.edu/aat/300205002 +http://vocab.getty.edu/aat/300019199 +http://vocab.getty.edu/aat/300055309 +http://vocab.getty.edu/aat/300311390 +http://vocab.getty.edu/aat/300389914 +http://vocab.getty.edu/aat/300387760 +http://vocab.getty.edu/aat/300390895 +http://vocab.getty.edu/aat/300404195 +http://vocab.getty.edu/aat/300419330 +http://vocab.getty.edu/aat/300443813 +http://vocab.getty.edu/aat/300387160 http://vocab.getty.edu/aat/300252927 -http://vocab.getty.edu/aat/300046167 -http://vocab.getty.edu/aat/300069053 -http://vocab.getty.edu/aat/300374955 -http://vocab.getty.edu/aat/300417433 +http://vocab.getty.edu/aat/300400658 +http://vocab.getty.edu/aat/300410382 +http://vocab.getty.edu/aat/300419983 +http://vocab.getty.edu/aat/300451360 +http://vocab.getty.edu/aat/300000905 +http://vocab.getty.edu/aat/300343680 +http://vocab.getty.edu/aat/300386447 +http://vocab.getty.edu/aat/300389684 +http://vocab.getty.edu/aat/300389906 +http://vocab.getty.edu/aat/300389908 +http://vocab.getty.edu/aat/300393173 +http://vocab.getty.edu/aat/300404810 http://vocab.getty.edu/aat/300410296 -http://vocab.getty.edu/aat/300002691 -http://vocab.getty.edu/aat/300041363 -http://vocab.getty.edu/aat/300264503 -http://vocab.getty.edu/aat/300003745 -http://vocab.getty.edu/aat/300263825 -http://vocab.getty.edu/aat/300343479 +http://vocab.getty.edu/aat/300379254 +http://vocab.getty.edu/aat/300264501 +http://vocab.getty.edu/aat/300053852 +http://vocab.getty.edu/aat/300312362 +http://vocab.getty.edu/aat/300395589 http://vocab.getty.edu/aat/300404656 http://vocab.getty.edu/aat/300410297 -http://vocab.getty.edu/aat/300013561 -http://vocab.getty.edu/aat/300017557 +http://vocab.getty.edu/aat/300017437 +http://vocab.getty.edu/aat/300343718 +http://vocab.getty.edu/aat/300386478 +http://vocab.getty.edu/aat/300389683 +http://vocab.getty.edu/aat/300395543 +http://vocab.getty.edu/aat/300417310 +http://vocab.getty.edu/aat/300021444 +http://vocab.getty.edu/aat/300263825 +http://vocab.getty.edu/aat/300024422 +http://vocab.getty.edu/aat/300249973 +http://vocab.getty.edu/aat/300343672 +http://vocab.getty.edu/aat/300310682 +http://vocab.getty.edu/aat/300443484 +http://vocab.getty.edu/aat/300264467 +http://vocab.getty.edu/aat/300265774 +http://vocab.getty.edu/aat/300265682 +http://vocab.getty.edu/aat/300310373 +http://vocab.getty.edu/aat/300343602 +http://vocab.getty.edu/aat/300375344 +http://vocab.getty.edu/aat/300393188 +http://vocab.getty.edu/aat/300400878 +http://vocab.getty.edu/aat/300417433 +http://vocab.getty.edu/aat/300161848 http://vocab.getty.edu/aat/300107503 -http://vocab.getty.edu/aat/300038634 -http://vocab.getty.edu/aat/300312155 -http://vocab.getty.edu/aat/300056550 -http://vocab.getty.edu/aat/300013055 -http://vocab.getty.edu/aat/300310312 -http://vocab.getty.edu/aat/300069057 -http://vocab.getty.edu/aat/300038459 -http://vocab.getty.edu/aat/300007231 -http://vocab.getty.edu/aat/300386794 -http://vocab.getty.edu/aat/300435165 +http://vocab.getty.edu/aat/300312147 +http://vocab.getty.edu/aat/300312239 +http://vocab.getty.edu/aat/300312367 +http://vocab.getty.edu/aat/300343721 +http://vocab.getty.edu/aat/300013305 +http://vocab.getty.edu/aat/300387783 +http://vocab.getty.edu/aat/300310153 +http://vocab.getty.edu/aat/300310700 +http://vocab.getty.edu/aat/300310701 +http://vocab.getty.edu/aat/300343893 +http://vocab.getty.edu/aat/300106840 +http://vocab.getty.edu/aat/300300970 +http://vocab.getty.edu/aat/300261258 +http://vocab.getty.edu/aat/300216057 +http://vocab.getty.edu/aat/300021931 http://vocab.getty.edu/aat/300017559 -http://vocab.getty.edu/aat/300013568 -http://vocab.getty.edu/aat/300013293 -http://vocab.getty.edu/aat/300127382 +http://vocab.getty.edu/aat/300189864 +http://vocab.getty.edu/aat/300013574 http://vocab.getty.edu/aat/300310154 -http://vocab.getty.edu/aat/300019199 -http://vocab.getty.edu/aat/300013499 -http://vocab.getty.edu/aat/300013788 -http://vocab.getty.edu/aat/300028749 -http://vocab.getty.edu/aat/300264462 +http://vocab.getty.edu/aat/300310505 +http://vocab.getty.edu/aat/300310702 +http://vocab.getty.edu/aat/300374823 +http://vocab.getty.edu/aat/300374834 +http://vocab.getty.edu/aat/300039221 +http://vocab.getty.edu/aat/300106854 http://vocab.getty.edu/aat/300162813 -http://vocab.getty.edu/aat/300265774 -http://vocab.getty.edu/aat/300395543 -http://vocab.getty.edu/aat/300012673 -http://vocab.getty.edu/aat/300055309 +http://vocab.getty.edu/aat/300013445 +http://vocab.getty.edu/aat/300021930 +http://vocab.getty.edu/aat/300021946 +http://vocab.getty.edu/aat/300021916 +http://vocab.getty.edu/aat/300037592 +http://vocab.getty.edu/aat/300013438 +http://vocab.getty.edu/aat/300264462 +http://vocab.getty.edu/aat/300212527 +http://vocab.getty.edu/aat/300038459 +http://vocab.getty.edu/aat/300310411 +http://vocab.getty.edu/aat/300191611 http://vocab.getty.edu/aat/300004479 -http://vocab.getty.edu/aat/300069634 -http://vocab.getty.edu/aat/300106840 -http://vocab.getty.edu/aat/300265699 -http://vocab.getty.edu/aat/300263133 -http://vocab.getty.edu/aat/300106854 +http://vocab.getty.edu/aat/300005246 +http://vocab.getty.edu/aat/300249920 +http://vocab.getty.edu/aat/300013834 +http://vocab.getty.edu/aat/300022022 +http://vocab.getty.edu/aat/300021932 +http://vocab.getty.edu/aat/300017557 +http://vocab.getty.edu/aat/300016566 +http://vocab.getty.edu/aat/300197148 +http://vocab.getty.edu/aat/300013055 +http://vocab.getty.edu/aat/300012929 +http://vocab.getty.edu/aat/300264396 +http://vocab.getty.edu/aat/300264540 +http://vocab.getty.edu/aat/300107466 http://vocab.getty.edu/aat/300265738 -http://vocab.getty.edu/aat/300343778 -http://vocab.getty.edu/aat/300055732 -http://vocab.getty.edu/aat/300069638 +http://vocab.getty.edu/aat/300014918 +http://vocab.getty.edu/aat/300212893 +http://vocab.getty.edu/aat/300298984 +http://vocab.getty.edu/aat/300022552 +http://vocab.getty.edu/aat/300007231 +http://vocab.getty.edu/aat/300265699 +http://vocab.getty.edu/aat/300343716 +http://vocab.getty.edu/aat/300005766 +http://vocab.getty.edu/aat/300003745 http://vocab.getty.edu/aat/300023433 -http://vocab.getty.edu/aat/300387160 -http://vocab.getty.edu/aat/300250055 -http://vocab.getty.edu/aat/300310505 -http://vocab.getty.edu/aat/300311390 -http://vocab.getty.edu/aat/300263134 -http://vocab.getty.edu/aat/300015638 -http://vocab.getty.edu/aat/300390895 -http://vocab.getty.edu/aat/300046300 -http://vocab.getty.edu/aat/300311178 -http://vocab.getty.edu/aat/300443813 -http://vocab.getty.edu/aat/300388786 -http://vocab.getty.edu/aat/300393755 +http://vocab.getty.edu/aat/300264400 +http://vocab.getty.edu/aat/300258325 +http://vocab.getty.edu/aat/300015033 +http://vocab.getty.edu/aat/300000597 +http://vocab.getty.edu/aat/300266236 +http://vocab.getty.edu/aat/300264417 +http://vocab.getty.edu/aat/300069057 +http://vocab.getty.edu/aat/300013910 +http://vocab.getty.edu/aat/300046167 +http://vocab.getty.edu/aat/300013788 +http://vocab.getty.edu/aat/300007466 +http://vocab.getty.edu/aat/300435165 diff --git a/sensitivity_markers/explicit/aat_termKind_all.csv b/sensitivity_markers/explicit/aat_termKind_all.csv index 086e70a..c51b023 100644 --- a/sensitivity_markers/explicit/aat_termKind_all.csv +++ b/sensitivity_markers/explicit/aat_termKind_all.csv @@ -1,52 +1,51 @@ concept,flag +http://vocab.getty.edu/aat/300056500,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300250608,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300255372,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300252337,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300261242,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310379,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310380,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310381,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310382,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310383,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300250139,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300250103,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310656,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300310440,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300252337,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310383,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300255372,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300255496,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310465,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300310466,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310382,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300250608,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310467,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310468,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300310469,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310379,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300250103,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300310577,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310468,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310381,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310380,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310656,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300017755,http://vocab.getty.edu/term/kind/Deprecated http://vocab.getty.edu/aat/300386060,http://vocab.getty.edu/term/kind/Deprecated -http://vocab.getty.edu/aat/300310467,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310465,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300056500,http://vocab.getty.edu/term/kind/Pejorative -http://vocab.getty.edu/aat/300375682,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310506,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300311371,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300017455,http://vocab.getty.edu/term/kind/Pejorative -http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Pejorative -http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Deprecated -http://vocab.getty.edu/aat/300016954,http://vocab.getty.edu/term/kind/AvoidUse http://vocab.getty.edu/aat/300212771,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300010739,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300011154,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300310690,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300017437,http://vocab.getty.edu/term/kind/AvoidUse -http://vocab.getty.edu/aat/300041759,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300006460,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300255278,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300046167,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300192108,http://vocab.getty.edu/term/kind/Deprecated -http://vocab.getty.edu/aat/300389818,http://vocab.getty.edu/term/kind/Deprecated -http://vocab.getty.edu/aat/300438481,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300343479,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300198896,http://vocab.getty.edu/term/kind/JargonOrSlang -http://vocab.getty.edu/aat/300411899,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300263133,http://vocab.getty.edu/term/kind/AvoidUse -http://vocab.getty.edu/aat/300230899,http://vocab.getty.edu/term/kind/Pejorative -http://vocab.getty.edu/aat/300380287,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300263134,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300041759,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300016954,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300343479,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300006460,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300017437,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300046167,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300386398,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300311371,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300017455,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300438481,http://vocab.getty.edu/term/kind/JargonOrSlang http://vocab.getty.edu/aat/300011112,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300380287,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300389818,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300230899,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300310506,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300010739,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310690,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300192108,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300255278,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300375682,http://vocab.getty.edu/term/kind/JargonOrSlang diff --git a/sensitivity_markers/explicit/aat_termKind_all_old.csv b/sensitivity_markers/explicit/aat_termKind_all_old.csv new file mode 100644 index 0000000..086e70a --- /dev/null +++ b/sensitivity_markers/explicit/aat_termKind_all_old.csv @@ -0,0 +1,52 @@ +concept,flag +http://vocab.getty.edu/aat/300261242,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300250139,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300250103,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310656,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310440,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300252337,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310383,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300255372,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300255496,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310466,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310382,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300250608,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310469,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310379,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310577,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310468,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310381,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310380,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300017755,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300386060,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300310467,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310465,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300056500,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300375682,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310506,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300311371,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300017455,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300443480,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300016954,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300212771,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300010739,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300011154,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300310690,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300017437,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300041759,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300006460,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300255278,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300046167,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300192108,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300389818,http://vocab.getty.edu/term/kind/Deprecated +http://vocab.getty.edu/aat/300438481,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300343479,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300198896,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300411899,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300263133,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300230899,http://vocab.getty.edu/term/kind/Pejorative +http://vocab.getty.edu/aat/300380287,http://vocab.getty.edu/term/kind/JargonOrSlang +http://vocab.getty.edu/aat/300263134,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300386398,http://vocab.getty.edu/term/kind/AvoidUse +http://vocab.getty.edu/aat/300011112,http://vocab.getty.edu/term/kind/JargonOrSlang diff --git a/sensitivity_markers/explicit/excluded_explicit.txt b/sensitivity_markers/explicit/excluded_explicit.txt new file mode 100644 index 0000000..59c8e31 --- /dev/null +++ b/sensitivity_markers/explicit/excluded_explicit.txt @@ -0,0 +1,19 @@ +For these Wikidata entities, P2552 explicit markers were excluded manually, because they were not relevant + +Q110768064 +Q112059263 +Q70894304 +Q21510852 +Q3938 +Q96200400 +Q96200400 +Q67085833 +Q67085833 +Q106537557 +Q15711994 +Q55640599 +Q106537557 +Q112078715 +Q96200400 +Q96200400 +Q106537557 \ No newline at end of file diff --git a/sensitivity_markers/explicit/explicit_all.csv b/sensitivity_markers/explicit/explicit_all.csv new file mode 100644 index 0000000..c77fd4f --- /dev/null +++ b/sensitivity_markers/explicit/explicit_all.csv @@ -0,0 +1,274 @@ +resource,lang,lemma,entity_id,explicit_marker,value,level +pwn,en,race,burnup.n.01,usage_domain,['slang.n.02'],1 +pwn,en,homosexual,butch.s.02,usage_domain,['slang.n.02'],2 +pwn,en,descent,chink.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +pwn,en,coolie,coolie.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",3 +pwn,en,homosexual,fagot.n.01,usage_domain,['disparagement.n.01'],3 +pwn,en,queer,fagot.n.01,usage_domain,['disparagement.n.01'],3 +pwn,en,lilliputian,fiddling.s.01,usage_domain,['colloquialism.n.01'],2 +pwn,en,queer,fishy.s.02,usage_domain,['colloquialism.n.01'],2 +pwn,en,descent,greaser.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +pwn,en,indian,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +pwn,en,caucasian,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +pwn,en,half-breed,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +pwn,en,headhunter,headhunter.n.01,usage_domain,['colloquialism.n.01'],1 +pwn,en,descent,jap.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +pwn,en,kaffir,kaffir.n.02,usage_domain,['disparagement.n.01'],3 +pwn,en,black,kaffir.n.02,usage_domain,['disparagement.n.01'],3 +pwn,en,descent,kraut.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +pwn,en,black,mammy.n.01,usage_domain,['disparagement.n.01'],1 +pwn,en,mongoloid,mongoloid.a.03,usage_domain,['disparagement.n.01'],3 +pwn,en,mongoloid,mongoloid.n.02,usage_domain,['disparagement.n.01'],3 +pwn,en,descent,paddy.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +pwn,en,black,pickaninny.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +pwn,en,race,pumped-up.s.01,usage_domain,['colloquialism.n.01'],1 +pwn,en,native,redskin.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +pwn,en,descent,spic.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +pwn,en,homosexual,straight.s.10,usage_domain,['colloquialism.n.01'],1 +pwn,en,white,white_trash.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +pwn,en,white,white-shoe.s.01,usage_domain,['colloquialism.n.01'],1 +pwn,en,white,whitey.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +pwn,en,descent,wop.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +wikidata,en,immigrant,Q1532765,P31,Q1371427,1 +wikidata,en,immigrant,Q55611664,P31,Q545779,1 +wikidata,en,barbarian,Q134313,P31,Q1371427,3 +wikidata,en,servant,Q10543172,P31,Q16335296,1 +wikidata,en,servant,Q1075791,P31,Q16335296,1 +wikidata,en,servant,Q303928,P31,Q16335296,1 +wikidata,en,servant,Q855855,P31,Q16335296,3 +wikidata,en,servant,Q3007620,P31,Q16335296,1 +wikidata,en,servant,Q3032660,P31,Q16335296,1 +wikidata,en,servant,Q5913718,P31,Q545779,1 +wikidata,en,servant,Q1412722,P31,Q16335296,1 +wikidata,en,gypsy,Q76475,P31,Q545779,1 +wikidata,en,white,Q7129609,P31,Q2042898,3 +wikidata,en,white,Q1066801,P31,Q545779,1 +wikidata,en,white,Q95530210,P31,Q545779,1 +wikidata,en,white,Q1135775,P31,Q545779,1 +wikidata,en,white,Q45991,P31,Q1371427,1 +wikidata,en,caucasian,Q7129609,P31,Q2042898,3 +wikidata,en,kaffir,Q1285250,P31,Q1371427,3 +wikidata,en,homosexual,Q165371,P31,Q1520214,1 +wikidata,en,page,Q855855,P31,Q16335296,3 +wikidata,en,negro,Q1130557,P31,Q1371427,3 +wikidata,en,negro,Q5913718,P31,Q545779,1 +wikidata,en,negro,Q1974358,P31,Q545779,1 +wikidata,en,mulatto,Q191923,P31,Q2042898,3 +wikidata,en,eskimo,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",1 +wikidata,en,gay,Q165371,P31,Q1520214,1 +wikidata,en,gay,Q898608,P31,Q545779,1 +wikidata,en,gay,Q55657493,P31,Q545779,1 +wikidata,en,inuit,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",1 +wikidata,en,black,Q1130557,P31,Q1371427,3 +wikidata,en,black,Q1455718,P31,Q1371427,1 +wikidata,en,black,Q1285250,P31,Q1371427,3 +wikidata,en,black,Q4117010,P31,Q1371427,1 +wikidata,en,black,Q45991,P31,Q1371427,1 +wikidata,en,queer,Q51415,P31,Q1520214,3 +wikidata,en,ethnic groups,Q112583744,P2559,created to avoid controversies around the question if French (Q121842) is an ethnic group. This should be an exception. Please don't create items for other ethnic or cultural groups in fiction.,1 +wikidata,en,trans,Q15711994,P2559,"This item is about a group of isomers and should be used in items describing a group of chemical entities, not a mixture of chemical entities (isomers)",1 +wikidata,en,race,Q989255,P2559,for Middle-Earth peoples use Q17412916,1 +wikidata,en,primitive,Q134313,P31,Q1371427,3 +wikidata,en,retarded,Q18394147,P31,Q22116852,3 +wikidata,en,slave,Q10076267,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",1 +wikidata,en,slave,Q1617492,P31,Q16335296,2 +wikidata,en,slave,Q12773225,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",3 +wikidata,en,slave,Q588083,P31,Q16335296,1 +wikidata,en,slave,Q4666486,P31,Q545779,1 +wikidata,en,ethnicity,Q112078715,P2559,Use as the value for statements with property P887,2 +wikidata,en,ethnicity,Q5101084,P31,Q545779,1 +wikidata,en,indigenous,Q1285250,P31,Q1371427,3 +wikidata,en,indigenous,Q5140747,P31,Q1371427,1 +wikidata,en,traditional,Q113570992,P31,Q16335296,1 +wikidata,nl,homo,Q1975772,P31,Q545779,1 +wikidata,nl,homo,Q55657493,P31,Q545779,1 +wikidata,nl,jap,Q1192767,P31,Q545779,3 +wikidata,nl,neger,Q1130557,P31,Q1371427,3 +wikidata,nl,bediende,Q855855,P31,Q16335296,3 +wikidata,nl,inuk,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",2 +wikidata,nl,homoseksueel,Q165371,P31,Q1520214,1 +wikidata,nl,queer,Q51415,P31,Q1520214,3 +wikidata,nl,zigeuner,Q76475,P31,Q545779,3 +wikidata,nl,zwart,Q1130557,P31,Q1371427,3 +wikidata,nl,kaukasisch,Q7129609,P31,Q2042898,3 +wikidata,nl,mulat,Q191923,P31,Q2042898,3 +wikidata,nl,ras,Q1130557,P31,Q1371427,3 +wikidata,nl,ras,Q7129609,P31,Q2042898,3 +wikidata,nl,ras,Q989255,P2559,for Middle-Earth peoples use Q17412916,2 +wikidata,nl,etnische groep,Q10969817,P31,Q545779,1 +wikidata,nl,barbaar,Q134313,P31,Q1371427,3 +wikidata,nl,slaaf,Q12773225,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",3 +wikidata,nl,eskimo,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",2 +wikidata,nl,page,Q855855,P31,Q16335296,3 +wikidata,nl,kaffer,Q1285250,P31,Q1371427,3 +wikidata,nl,wit,Q1135775,P31,Q545779,1 +aat,en,immigrant,300443480,termKind,"['Pejorative', 'Deprecated']",2 +aat,en,indian,300310567,historicFlag,,1 +aat,en,indian,300016954,historicFlag,,2 +aat,en,indian,300016954,termKind,['AvoidUse'],2 +aat,en,indian,300017557,historicFlag,,1 +aat,en,indian,300017559,historicFlag,,1 +aat,en,indian,300389906,historicFlag,,1 +aat,en,indian,300011154,termKind,['JargonOrSlang'],1 +aat,en,indian,300013641,historicFlag,,1 +aat,en,indian,300017437,historicFlag,,3 +aat,en,indian,300017437,termKind,['AvoidUse'],3 +aat,en,indian,300013055,historicFlag,,1 +aat,en,homo,300310690,termKind,['JargonOrSlang'],2 +aat,en,hottentot,300016575,historicFlag,,3 +aat,en,white,300261258,historicFlag,,1 +aat,en,white,300250103,termKind,['JargonOrSlang'],1 +aat,en,white,300310656,termKind,['JargonOrSlang'],1 +aat,en,white,300404195,historicFlag,,1 +aat,en,white,300380504,historicFlag,,1 +aat,en,white,300264417,historicFlag,,1 +aat,en,white,300013647,historicFlag,,1 +aat,en,white,300310312,historicFlag,,1 +aat,en,white,300013788,historicFlag,,1 +aat,en,white,300012673,historicFlag,,1 +aat,en,white,300343778,historicFlag,,1 +aat,en,white,300390895,historicFlag,,1 +aat,en,descent,300016575,historicFlag,,3 +aat,en,mongoloid,300017437,historicFlag,,3 +aat,en,mongoloid,300017437,termKind,['AvoidUse'],3 +aat,en,mongoloid,300389818,termKind,['Deprecated'],2 +aat,en,pygmy,300310411,historicFlag,,2 +aat,en,pygmy,300310577,termKind,['JargonOrSlang'],1 +aat,en,second world,300265774,historicFlag,,2 +aat,en,native,300343602,historicFlag,,1 +aat,en,native,300400499,historicFlag,,1 +aat,en,native,300393173,historicFlag,,1 +aat,en,native,300389906,historicFlag,,1 +aat,en,native,300389908,historicFlag,,1 +aat,en,native,300389683,historicFlag,,1 +aat,en,native,300389684,historicFlag,,1 +aat,en,native,300343716,historicFlag,,1 +aat,en,native,300374834,historicFlag,,1 +aat,en,native,300375344,historicFlag,,1 +aat,en,native,300343680,historicFlag,,1 +aat,en,native,300375682,termKind,['JargonOrSlang'],1 +aat,en,native,300017455,termKind,['Pejorative'],3 +aat,en,native,300016954,historicFlag,,2 +aat,en,native,300016954,termKind,['AvoidUse'],2 +aat,en,native,300386447,historicFlag,,1 +aat,en,native,300266236,historicFlag,,1 +aat,en,native,300250608,termKind,['JargonOrSlang'],1 +aat,en,native,300374823,historicFlag,,1 +aat,en,native,300017437,historicFlag,,3 +aat,en,native,300017437,termKind,['AvoidUse'],3 +aat,en,native,300310577,termKind,['JargonOrSlang'],1 +aat,en,native,300343718,historicFlag,,1 +aat,en,native,300343721,historicFlag,,1 +aat,en,native,300389818,termKind,['Deprecated'],2 +aat,en,native,300017557,historicFlag,,1 +aat,en,native,300017559,historicFlag,,1 +aat,en,native,300343778,historicFlag,,1 +aat,en,native,300056500,historicFlag,,3 +aat,en,native,300056500,termKind,['Pejorative'],3 +aat,en,berber,300443574,historicFlag,,1 +aat,en,roots,300343602,historicFlag,,1 +aat,en,roots,300265699,historicFlag,,1 +aat,en,western,300389906,historicFlag,,1 +aat,en,western,300343680,historicFlag,,1 +aat,en,western,300310373,historicFlag,,1 +aat,en,western,300021930,historicFlag,,1 +aat,en,western,300016566,historicFlag,,1 +aat,en,western,300264400,historicFlag,,1 +aat,en,western,300343721,historicFlag,,1 +aat,en,western,300013561,historicFlag,,1 +aat,en,western,300069057,historicFlag,,1 +aat,en,western,300012673,historicFlag,,1 +aat,en,western,300106854,historicFlag,,1 +aat,en,western,300343778,historicFlag,,1 +aat,en,aboriginal,300312155,historicFlag,,1 +aat,en,eskimo,300017437,historicFlag,,3 +aat,en,eskimo,300017437,termKind,['AvoidUse'],3 +aat,en,eskimo,300389818,termKind,['Deprecated'],2 +aat,en,eskimo,300017455,termKind,['Pejorative'],3 +aat,en,hermaphrodite,300386060,termKind,['Deprecated'],3 +aat,en,indo,300386794,historicFlag,,3 +aat,en,oriental,300410382,historicFlag,,1 +aat,en,oriental,300022022,historicFlag,,2 +aat,en,oriental,300041759,historicFlag,,1 +aat,en,oriental,300041759,termKind,['JargonOrSlang'],1 +aat,en,colored,300252337,termKind,['JargonOrSlang'],1 +aat,en,colored,300310552,historicFlag,,1 +aat,en,colored,300013788,historicFlag,,1 +aat,en,inuit,300017455,termKind,['Pejorative'],3 +aat,en,black,300261258,historicFlag,,1 +aat,en,black,300375682,termKind,['JargonOrSlang'],1 +aat,en,black,300310656,termKind,['JargonOrSlang'],1 +aat,en,black,300400883,historicFlag,,1 +aat,en,black,300013568,historicFlag,,1 +aat,en,dwarf,300310411,historicFlag,,2 +aat,en,dwarf,300310690,termKind,['JargonOrSlang'],2 +aat,en,race,300000597,historicFlag,,1 +aat,en,primitive,300069057,historicFlag,,1 +aat,en,primitive,300310154,historicFlag,,1 +aat,en,primitive,300056500,historicFlag,,3 +aat,en,primitive,300056500,termKind,['Pejorative'],3 +aat,en,slave,300230899,termKind,['Pejorative'],3 +aat,en,slave,300055309,historicFlag,,2 +aat,en,primitivism,300056500,historicFlag,,3 +aat,en,primitivism,300056500,termKind,['Pejorative'],3 +aat,en,indigenous,300387760,historicFlag,,1 +aat,en,indigenous,300017437,historicFlag,,3 +aat,en,indigenous,300017437,termKind,['AvoidUse'],3 +aat,en,indigenous,300389818,termKind,['Deprecated'],2 +aat,en,indigenous,300264462,historicFlag,,1 +aat,en,indigenous,300056500,historicFlag,,3 +aat,en,indigenous,300056500,termKind,['Pejorative'],3 +aat,en,traditional,300021946,historicFlag,,1 +aat,en,traditional,300021930,historicFlag,,1 +aat,en,traditional,300264462,historicFlag,,1 +aat,en,traditional,300106840,historicFlag,,1 +aat,en,tribe,300438481,termKind,['JargonOrSlang'],1 +aat,en,tribe,300017557,historicFlag,,1 +aat,en,tribe,300017559,historicFlag,,1 +odwn,nl,exotisch,odwn-10-108298613-n,pragmatics_chronology,['oldfashioned'],1 +odwn,nl,lilliputter,eng-30-10040344-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,homo,eng-30-10254965-n,pragmatics_connotation,['pejorative'],2 +odwn,nl,homo,eng-30-10076033-n,pragmatics_connotation,"['pejorative', 'offensive']",2 +odwn,nl,mongool,eng-30-10197525-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +odwn,nl,jap,odwn-10-103201483-n,pragmatics_connotation,['offensive'],3 +odwn,nl,westers,eng-30-10386312-n,pragmatics_connotation,['pejorative'],1 +odwn,nl,homoseksualiteit,eng-30-00856847-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,neger,eng-30-06201908-n,pragmatics_connotation,['pejorative'],2 +odwn,nl,neger,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,neger,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +odwn,nl,afkomst,eng-30-07970721-n,pragmatics_chronology,['oldfashioned'],2 +odwn,nl,blank,eng-30-05600637-n,pragmatics_chronology,['oldfashioned'],1 +odwn,nl,blank,eng-30-05600637-n,pragmatics_connotation,['pejorative'],1 +odwn,nl,knecht,eng-30-09815790-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,knecht,eng-30-09815790-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,jappenkamp,r_n-38586,pragmatics_connotation,['euphemistic'],2 +odwn,nl,homoseksueel,eng-30-10076033-n,pragmatics_connotation,"['pejorative', 'offensive']",2 +odwn,nl,stam,eng-30-07970721-n,pragmatics_chronology,['oldfashioned'],2 +odwn,nl,zwart,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,zwart,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +odwn,nl,zwart,eng-30-09859038-n,pragmatics_connotation,['pejorative'],2 +odwn,nl,zwart,odwn-10-103179400-n,pragmatics_connotation,['pejorative'],1 +odwn,nl,zwart,eng-30-08549292-n,pragmatics_connotation,['pejorative'],1 +odwn,nl,zwart,eng-30-01091905-n,pragmatics_chronology,['oldfashioned'],1 +odwn,nl,traditioneel,r_n-41933,pragmatics_connotation,['pejorative'],1 +odwn,nl,primitief,eng-30-10553402-n,pragmatics_connotation,['offensive'],3 +odwn,nl,dwerg,eng-30-10040344-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,indisch,eng-30-02503517-n,pragmatics_connotation,['jocular'],2 +odwn,nl,achterlijk,eng-30-10100761-n,pragmatics_connotation,"['pejorative', 'offensive']",1 +odwn,nl,ras,odwn-10-105393011-n,pragmatics_connotation,['offensive'],1 +odwn,nl,barbaar,eng-30-10553402-n,pragmatics_connotation,['offensive'],3 +odwn,nl,barbaar,eng-30-00386390-v,pragmatics_chronology,['oldfashioned'],2 +odwn,nl,barbaar,eng-30-10410815-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,barbaar,eng-30-10410815-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +odwn,nl,barbaar,eng-30-09879297-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,mohammedaan,odwn-10-107075238-n,pragmatics_chronology,['oldfashioned'],2 +odwn,nl,moor,odwn-10-102610292-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,moor,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,moor,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +odwn,nl,gehandicapte,eng-30-05139094-n,pragmatics_chronology,['oldfashioned'],2 +odwn,nl,gehandicapte,eng-30-10197525-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +odwn,nl,koelie,eng-30-10035809-n,pragmatics_connotation,['pejorative'],3 +odwn,nl,kaffer,eng-30-10410815-n,pragmatics_chronology,['oldfashioned'],3 +odwn,nl,kaffer,eng-30-10410815-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +odwn,nl,kaffer,odwn-10-100082478-n,pragmatics_connotation,['offensive'],3 +odwn,nl,wit,eng-30-03672521-n,pragmatics_chronology,['oldfashioned'],1 \ No newline at end of file diff --git a/sensitivity_markers/explicit/explicit_by_levels.ipynb b/sensitivity_markers/explicit/explicit_by_levels.ipynb new file mode 100644 index 0000000..e0186fd --- /dev/null +++ b/sensitivity_markers/explicit/explicit_by_levels.ipynb @@ -0,0 +1,595 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import csv\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "def get_lemma_by_term(query_term:str, lang:str) -> str:\n", + " '''\n", + " Getting a lemma of a query term\n", + " lang: str, 'en' or 'nl'\n", + " Returns str, 'not found' if lemma was not found\n", + " '''\n", + " \n", + " return_lemma = 'not found'\n", + " \n", + " # importing query terms with lemmas\n", + " # change path to GitHub\n", + " \n", + " with open('/Users/anesterov/reps/LODlit/query_terms.json','r') as jf:\n", + " query_terms = json.load(jf)\n", + " \n", + " for lemma, qt in query_terms[lang].items():\n", + " if query_term in qt:\n", + " return_lemma = lemma\n", + " \n", + " return return_lemma" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Wikidata" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 1. Check if QIDs have explicit markers by lang by markers -> df\n", + "# 2. remove duplicates by QID, lemma, lang" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "wd_explicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\",\"value\",\"level\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "lang = \"nl\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# importing all search results\n", + "with open(f\"/Users/anesterov/LODlit_local/wd/jan31/results_clean_{lang}.json\",'r') as jf:\n", + " wd_all = json.load(jf)\n", + "\n", + "# import subset\n", + "with open(f\"/Users/anesterov/reps/LODlit/Wikidata/wd_{lang}_subset.json\",'r') as jf:\n", + " wd_subset = json.load(jf)\n", + "\n", + "# get all QIDs in the subset\n", + "subset_quids = []\n", + "for hits in wd_subset.values():\n", + " for hit in hits:\n", + " subset_quids.append(hit[\"QID\"])\n", + "\n", + "# import rm\n", + "wd_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + "rm_quids = list(wd_rm[wd_rm[\"resource\"] == \"wikidata\"][wd_rm[\"lang\"] == lang][\"entity_id\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import P31 markers\n", + "p31 = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/wikidata_P31_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# make a dict of entity and value\n", + "p31_pairs = {}\n", + "for row in p31.iterrows():\n", + " p31_pairs[row[1][\"item\"].lstrip(\"http://www.wikidata.org/entity/\")] = row[1][\"instance_of\"].lstrip(\"http://www.wikidata.org/entity/\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import P2559 markers\n", + "p2559 = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/wikidata_P2559_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "p2559_pairs = {}\n", + "for row in p2559.iterrows():\n", + " p2559_pairs[row[1][\"item\"].lstrip(\"http://www.wikidata.org/entity/\")] = row[1][\"usage_instructions\"]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "for term, hits in wd_all.items():\n", + " lemma = get_lemma_by_term(term, lang)\n", + " \n", + " for hit in hits:\n", + " # if p31 markers \n", + " if hit[\"QID\"] in p31_pairs.keys():\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if hit[\"QID\"] in set(subset_quids):\n", + " level = \"2\"\n", + " if hit[\"QID\"] in set(rm_quids):\n", + " level = \"3\"\n", + " \n", + " row = [\"wikidata\",lang,lemma,hit[\"QID\"],\"P31\",p31_pairs[hit[\"QID\"]],level]\n", + " wd_explicit.loc[len(wd_explicit)] = row\n", + " \n", + " # if p2559 markers \n", + " if hit[\"QID\"] in p2559_pairs.keys():\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if hit[\"QID\"] in set(subset_quids):\n", + " level = \"2\"\n", + " if hit[\"QID\"] in set(rm_quids):\n", + " level = \"3\"\n", + " \n", + " row = [\"wikidata\",lang,lemma,hit[\"QID\"],\"P2559\",p2559_pairs[hit[\"QID\"]],level]\n", + " wd_explicit.loc[len(wd_explicit)] = row" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "wd_explicit.drop_duplicates([\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\",\"value\"],ignore_index=True).to_csv(\"wd_explicit.csv\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## AAT" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_explicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\",\"value\",\"level\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "lang = \"en\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# importing all search results\n", + "with open(f\"/Users/anesterov/reps/LODlit/AAT/aat_query_results_{lang}.json\",'r') as jf:\n", + " aat_all = json.load(jf)\n", + "\n", + "# import subset\n", + "with open(f\"/Users/anesterov/reps/LODlit/AAT/aat_{lang}_subset.json\",'r') as jf:\n", + " aat_subset = json.load(jf)\n", + "\n", + "# get all QIDs in the subset\n", + "subset = []\n", + "for hits in aat_subset.values():\n", + " for hit in hits:\n", + " subset.append(hit[\"aat_uri\"])\n", + "\n", + "# import rm\n", + "aat_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + "rm = list(aat_rm[aat_rm[\"resource\"] == \"aat\"][aat_rm[\"lang\"] == lang][\"entity_id\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "strip_part = \"http://vocab.getty.edu/aat/\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import historicFlag markers\n", + "historic_flag = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/aat_historicFlag_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "historic_flag_list = list(set([c.lstrip(strip_part) for c in historic_flag[\"concept\"]]))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import termKind markers\n", + "termKind_flag = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/aat_termKind_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "for group in wd_en_implicit.groupby([\"lemma\",\"entity_id\",\"value\"]):\n", + " if (len(group[1])) > 1:\n", + " grouped_markers = (list(group[1][\"implicit_marker\"]))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# make a dict of concepts with flags\n", + "# !NB several labels can be marked, make a list\n", + "termKind_flag_pairs = {}\n", + "for group in termKind_flag.groupby(\"concept\"):\n", + " grouped_flags = list(group[1][\"flag\"])\n", + " termKind_flag_pairs[str(group[0]).lstrip(strip_part)] = [f.lstrip(\"http://vocab.getty.edu/term/kind/\") for f in grouped_flags]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "termKind_flag_pairs" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "for term, hits in aat_all.items():\n", + " lemma = get_lemma_by_term(term, lang)\n", + " \n", + " for hit in hits:\n", + " # if historic_flag markers\n", + " if hit[\"aat_uri\"] in historic_flag_list:\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if hit[\"aat_uri\"] in set(subset):\n", + " level = \"2\"\n", + " if hit[\"aat_uri\"] in set(rm):\n", + " level = \"3\"\n", + " \n", + " row = [\"aat\",lang,lemma,hit[\"aat_uri\"],\"historicFlag\",\"\",level]\n", + " aat_explicit.loc[len(aat_explicit)] = row\n", + " \n", + " # if termKind flag\n", + " if hit[\"aat_uri\"] in termKind_flag_pairs.keys():\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if hit[\"aat_uri\"] in set(subset):\n", + " level = \"2\"\n", + " if hit[\"aat_uri\"] in set(rm):\n", + " level = \"3\"\n", + " \n", + " row = [\"aat\",lang,lemma,hit[\"aat_uri\"],\"termKind\",termKind_flag_pairs[hit[\"aat_uri\"]],level]\n", + " aat_explicit.loc[len(aat_explicit)] = row" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_explicit" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_explicit.drop_duplicates([\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\"],ignore_index=True).to_csv(\"aat_explicit.csv\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## PWN" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "pwn_explicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\",\"value\",\"level\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# importing all search results\n", + "with open(\"/Users/anesterov/reps/LODlit/PWN/pwn31_query_results.json\",'r') as jf:\n", + " pwn_all = json.load(jf)\n", + "\n", + "# import subset\n", + "with open(\"/Users/anesterov/reps/LODlit/PWN/pwn_subset.json\",'r') as jf:\n", + " pwn_subset = json.load(jf)\n", + "\n", + "# get all QIDs in the subset\n", + "subset = []\n", + "for hits in pwn_subset.values():\n", + " for hit in hits:\n", + " subset.append(hit[\"synset_id\"])\n", + "\n", + "# import rm\n", + "pwn_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + "rm = list(pwn_rm[pwn_rm[\"resource\"] == \"pwn\"][\"entity_id\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import pwn markers\n", + "usage_domains = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/pwn_usage_domain_synsets_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "usage_domains_pairs = {}\n", + "for row in usage_domains.iterrows():\n", + " usage_domains_pairs[row[1][\"synset_id\"]] = \\\n", + " row[1][\"usage_domains\"].replace(\"[\",\"\").replace(\"]\",\"\").replace(\"'\",\"\").replace(\" \",\"\").split(\",\")\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "for term, hits in pwn_all.items():\n", + " lemma = get_lemma_by_term(term, \"en\")\n", + " \n", + " for hit in hits:\n", + " # if historic_flag markers\n", + " if hit[\"synset_id\"] in usage_domains_pairs.keys():\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if hit[\"synset_id\"] in set(subset):\n", + " level = \"2\"\n", + " if hit[\"synset_id\"] in set(rm):\n", + " level = \"3\"\n", + " \n", + " row = [\"pwn\",\"en\",lemma,hit[\"synset_id\"],\"usage_domain\",usage_domains_pairs[hit[\"synset_id\"]],level]\n", + " pwn_explicit.loc[len(pwn_explicit)] = row" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "pwn_explicit.drop_duplicates([\"lemma\",\"entity_id\"],ignore_index=True).to_csv(\"pwn_explicit.csv\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## ODWN" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "odwn_explicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"explicit_marker\",\"value\",\"level\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# importing all search results\n", + "with open(\"/Users/anesterov/reps/LODlit/ODWN/odwn_query_results.json\",'r') as jf:\n", + " odwn_all = json.load(jf)\n", + "\n", + "# import subset\n", + "with open(\"/Users/anesterov/reps/LODlit/ODWN/odwn_subset.json\",'r') as jf:\n", + " odwn_subset = json.load(jf)\n", + "\n", + "# get all ids in the subset\n", + "subset = []\n", + "for hits in odwn_subset.values():\n", + " for hit in hits:\n", + " if hit[\"synset_id\"] != \"\":\n", + " subset.append(hit[\"synset_id\"])\n", + " else:\n", + " subset.append(hit[\"sense_id\"])\n", + "\n", + "# import rm\n", + "odwn_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + "rm = list(odwn_rm[odwn_rm[\"resource\"] == \"odwn\"][\"entity_id\"])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# import odwn markers\n", + "with open(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/odwn_all_pragmatics.json\",'r') as jf:\n", + " odwn_markers = json.load(jf)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "for term, hits in odwn_all.items():\n", + " lemma = get_lemma_by_term(term, \"nl\")\n", + " \n", + " for hit in hits:\n", + " \n", + " if hit[\"synset_id\"] != \"\":\n", + " odwn_id = hit[\"synset_id\"]\n", + " else:\n", + " odwn_id = hit[\"sense_id\"]\n", + " \n", + " # check level\n", + " level = \"1\"\n", + " if odwn_id in set(subset):\n", + " level = \"2\"\n", + " if odwn_id in set(rm):\n", + " level = \"3\"\n", + " \n", + " # get markers values for each synset/sense\n", + " # NB! collects pragmatics values of all lemmas in a synset\n", + " chron = list(set([le[\"pragmatics\"][\"chronology\"] for le in odwn_markers[odwn_id] if le[\"pragmatics\"][\"chronology\"]]))\n", + " conn = list(set([le[\"pragmatics\"][\"connotation\"] for le in odwn_markers[odwn_id] if le[\"pragmatics\"][\"connotation\"]]))\n", + " \n", + " if len(chron) > 0:\n", + " row = [\"odwn\",\"nl\",lemma,odwn_id,\"pragmatics_chronology\",chron,level]\n", + " odwn_explicit.loc[len(odwn_explicit)] = row\n", + "\n", + " if len(conn) > 0:\n", + " row = [\"odwn\",\"nl\",lemma,odwn_id,\"pragmatics_connotation\",conn,level]\n", + " odwn_explicit.loc[len(odwn_explicit)] = row" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "odwn_explicit.drop_duplicates([\"lemma\",\"entity_id\",\"explicit_marker\"],ignore_index=True).to_csv(\"odwn_explicit.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.5" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/sensitivity_markers/explicit/odwn_explicit.csv b/sensitivity_markers/explicit/odwn_explicit.csv new file mode 100644 index 0000000..fa41250 --- /dev/null +++ b/sensitivity_markers/explicit/odwn_explicit.csv @@ -0,0 +1,48 @@ +,resource,lang,lemma,entity_id,explicit_marker,value,level +0,odwn,nl,exotisch,odwn-10-108298613-n,pragmatics_chronology,['oldfashioned'],1 +1,odwn,nl,lilliputter,eng-30-10040344-n,pragmatics_connotation,['pejorative'],3 +2,odwn,nl,homo,eng-30-10254965-n,pragmatics_connotation,['pejorative'],2 +3,odwn,nl,homo,eng-30-10076033-n,pragmatics_connotation,"['pejorative', 'offensive']",2 +4,odwn,nl,mongool,eng-30-10197525-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +5,odwn,nl,jap,odwn-10-103201483-n,pragmatics_connotation,['offensive'],3 +6,odwn,nl,westers,eng-30-10386312-n,pragmatics_connotation,['pejorative'],1 +7,odwn,nl,homoseksualiteit,eng-30-00856847-n,pragmatics_connotation,['pejorative'],3 +8,odwn,nl,neger,eng-30-06201908-n,pragmatics_connotation,['pejorative'],2 +9,odwn,nl,neger,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +10,odwn,nl,neger,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +11,odwn,nl,afkomst,eng-30-07970721-n,pragmatics_chronology,['oldfashioned'],2 +12,odwn,nl,blank,eng-30-05600637-n,pragmatics_chronology,['oldfashioned'],1 +13,odwn,nl,blank,eng-30-05600637-n,pragmatics_connotation,['pejorative'],1 +14,odwn,nl,knecht,eng-30-09815790-n,pragmatics_chronology,['oldfashioned'],3 +15,odwn,nl,knecht,eng-30-09815790-n,pragmatics_connotation,['pejorative'],3 +16,odwn,nl,jappenkamp,r_n-38586,pragmatics_connotation,['euphemistic'],2 +17,odwn,nl,homoseksueel,eng-30-10076033-n,pragmatics_connotation,"['pejorative', 'offensive']",2 +18,odwn,nl,stam,eng-30-07970721-n,pragmatics_chronology,['oldfashioned'],2 +19,odwn,nl,zwart,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +20,odwn,nl,zwart,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +21,odwn,nl,zwart,eng-30-09859038-n,pragmatics_connotation,['pejorative'],2 +22,odwn,nl,zwart,odwn-10-103179400-n,pragmatics_connotation,['pejorative'],1 +23,odwn,nl,zwart,eng-30-08549292-n,pragmatics_connotation,['pejorative'],1 +24,odwn,nl,zwart,eng-30-01091905-n,pragmatics_chronology,['oldfashioned'],1 +25,odwn,nl,traditioneel,r_n-41933,pragmatics_connotation,['pejorative'],1 +26,odwn,nl,primitief,eng-30-10553402-n,pragmatics_connotation,['offensive'],3 +27,odwn,nl,dwerg,eng-30-10040344-n,pragmatics_connotation,['pejorative'],3 +28,odwn,nl,indisch,eng-30-02503517-n,pragmatics_connotation,['jocular'],2 +29,odwn,nl,achterlijk,eng-30-10100761-n,pragmatics_connotation,"['pejorative', 'offensive']",1 +30,odwn,nl,ras,odwn-10-105393011-n,pragmatics_connotation,['offensive'],1 +31,odwn,nl,barbaar,eng-30-10553402-n,pragmatics_connotation,['offensive'],3 +32,odwn,nl,barbaar,eng-30-00386390-v,pragmatics_chronology,['oldfashioned'],2 +33,odwn,nl,barbaar,eng-30-10410815-n,pragmatics_chronology,['oldfashioned'],3 +34,odwn,nl,barbaar,eng-30-10410815-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +35,odwn,nl,barbaar,eng-30-09879297-n,pragmatics_connotation,['pejorative'],3 +36,odwn,nl,mohammedaan,odwn-10-107075238-n,pragmatics_chronology,['oldfashioned'],2 +37,odwn,nl,moor,odwn-10-102610292-n,pragmatics_chronology,['oldfashioned'],3 +38,odwn,nl,moor,eng-30-09638009-n,pragmatics_chronology,['oldfashioned'],3 +39,odwn,nl,moor,eng-30-09638009-n,pragmatics_connotation,['offensive'],3 +40,odwn,nl,gehandicapte,eng-30-05139094-n,pragmatics_chronology,['oldfashioned'],2 +41,odwn,nl,gehandicapte,eng-30-10197525-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +42,odwn,nl,koelie,eng-30-10035809-n,pragmatics_connotation,['pejorative'],3 +43,odwn,nl,kaffer,eng-30-10410815-n,pragmatics_chronology,['oldfashioned'],3 +44,odwn,nl,kaffer,eng-30-10410815-n,pragmatics_connotation,"['pejorative', 'offensive']",3 +45,odwn,nl,kaffer,odwn-10-100082478-n,pragmatics_connotation,['offensive'],3 +46,odwn,nl,wit,eng-30-03672521-n,pragmatics_chronology,['oldfashioned'],1 diff --git a/sensitivity_markers/explicit/odwn_synsets_pragmatics.json b/sensitivity_markers/explicit/odwn_synsets_pragmatics.json deleted file mode 100644 index a01e538..0000000 --- a/sensitivity_markers/explicit/odwn_synsets_pragmatics.json +++ /dev/null @@ -1 +0,0 @@ -{"eng-30-14052403-n": [{"le_id": "aandoening-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "medicine"}}, {"le_id": "affectie-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "gebrek-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "medicine"}}, {"le_id": "gebrekkigheid-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "handicap-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "ongemak-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10626439-n": [{"le_id": "medicijnman-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "medicine"}}], "eng-30-10040344-n": [{"le_id": "dwerg--n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "mini--n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "dwerg-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "lilliputter-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}], "eng-30-10182913-n": [{"le_id": "homoseksuele-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "sodemiet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "sodemieter-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "reetkever-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "poot-n-11", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "holtor-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "ge\u00efnverteerde-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "gay-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "flikker-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bruinwerker-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "mietje-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "nicht-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "homo-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "homofiel-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "homoseksueel-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10197525-n": [{"le_id": "kretijn-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "mogool-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "mongool-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "cretin-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "debiel-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "geesteszieke-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "gek-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "gestoorde-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "idioot-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "imbeciel-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "krankzinnige-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "waanzinnige-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-107179852-n": [{"le_id": "mongool-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-103201483-n": [{"le_id": "Jap-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}], "odwn-10-100569798-n": [{"le_id": "islamiet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "religion"}}], "eng-30-04799133-n": [{"le_id": "etniciteit-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-00856847-n": [{"le_id": "homoseksualiteit-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "sodomie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}], "eng-30-00858060-n": [{"le_id": "bestialiteit-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "homofilie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "homoseksualiteit-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "zo\u00f6filie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-09638009-n": [{"le_id": "moor-n-1", "pragmatics": {"register": null, "geography": null, "chronology": "oldfashioned", "connotation": null, "domain": null}}, {"le_id": "neger-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "negerin-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "nikker-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "roetmop-n-1", "pragmatics": {"register": null, "geography": null, "chronology": "oldfashioned", "connotation": "offensive", "domain": null}}, {"le_id": "zwarte-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10582154-n": [{"le_id": "hulpje-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "hulp-n-5", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bediende-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-108184026-n": [{"le_id": "hermafrodiet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "biology"}}], "odwn-10-106518418-n": [{"le_id": "Indiaan-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "eng-30-08510456-n": [{"le_id": "komaf-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "oorsprong-n-5", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "herkomst-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "afkomst-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "origine-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bakermat-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "haard-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "kraamkamer-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "wieg-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-04923743-n": [{"le_id": "afkomst-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "afstamming-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}, {"le_id": "descendentie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "geboorte-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "herkomst-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "komaf-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-103541331-n": [{"le_id": "blanke-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-08903872-n": [{"le_id": "Mumbai-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "Bombay-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-09815790-n": [{"le_id": "assistent-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "helper-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "hulp-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "dienstknecht-n-1", "pragmatics": {"register": "formal", "geography": null, "chronology": "oldfashioned", "connotation": null, "domain": null}}, {"le_id": "knecht-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "waterdrager-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}], "eng-30-07969695-n": [{"le_id": "soortgenoten-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "sibbe-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "clan-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "stam-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}, {"le_id": "volksstam-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}], "eng-30-10157549-n": [{"le_id": "halfbloed-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "kleurling-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10154186-n": [{"le_id": "Roma-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "zigeunerin-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "gipsy-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "zigeuner-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-103272943-n": [{"le_id": "bosneger-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "odwn-10-107793684-n": [{"le_id": "ontwikkelingsland-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "economy"}}], "odwn-10-100513750-n": [{"le_id": "mesties-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-09627462-n": [{"le_id": "primitief-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "art"}}, {"le_id": "primitieven-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-02154508-v": [{"le_id": "opsporen-v-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "detecteren-v-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "ontdekken-v-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "vinden-v-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10163452-n": [{"le_id": "koppensneller-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-104714918-n": [{"le_id": "inlander-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-106744972-n": [{"le_id": "baboe-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-101847342-n": [{"le_id": "Berber-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "eng-30-10496626-n": [{"le_id": "pygmee-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "odwn-10-106536961-n": [{"le_id": "mulat-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}], "odwn-10-101180571-n": [{"le_id": "aboriginal-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "eng-30-10726031-n": [{"le_id": "tootsie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "transvestiet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "travestiet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10553402-n": [{"le_id": "barbaar-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "kannibaal-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "natuurmens-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "wilde-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10410815-n": [{"le_id": "primitieveling-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "barbaar-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "boer-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "boerenhufter-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "boerenkaffer-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "boerenkarhengst-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "boerenkinkel-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "boerenlul-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "boerenpummel-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "botterik-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "grobbejanus-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "heikneuter-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "hork-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "hufter-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "kaffer-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "kinkel-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "lomperd-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "lomperik-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "palurk-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "plebejer-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "plomperd-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "proleet-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "pummel-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}, {"le_id": "raudauwer-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "rouwdouw-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "rouwdouwer-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "vlegel-n-3", "pragmatics": {"register": null, "geography": null, "chronology": "oldfashioned", "connotation": "offensive", "domain": null}}, {"le_id": "woudezel-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-09879297-n": [{"le_id": "schelm-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "hooligan-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "schurk-n-6", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "barbaar-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "beest-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "beestmens-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "beul-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bloedhond-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bruut-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "bullebak-n-1", "pragmatics": {"register": "informal", "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}, {"le_id": "kwelduivel-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "kwelgeest-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "monster-n-4", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "nero-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "onmens-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "pestkop-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "plaag-n-3", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "plaagal-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "plaaggeest-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "plaagstok-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "sar-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "treiteraar-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "wreedaard-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10609325-n": [{"le_id": "heloot-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "lijfeigene-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "slaaf-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}, {"le_id": "slavin-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-06918215-n": [{"le_id": "Eskimo-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "geography"}}], "odwn-10-106171034-n": [{"le_id": "inboorling-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "anthropology"}}], "eng-30-06941479-n": [{"le_id": "Hottentot-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "Hottentots-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-08903636-n": [{"le_id": "Kolkata-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "Calcutta-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-107525787-n": [{"le_id": "mohammedaan-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": "religion"}}], "eng-30-08904392-n": [{"le_id": "Chennai-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "Madras-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-102610292-n": [{"le_id": "Moor-n-2", "pragmatics": {"register": null, "geography": null, "chronology": "oldfashioned", "connotation": null, "domain": null}}], "eng-30-10158756-n": [{"le_id": "gehandicapte-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "eng-30-10035809-n": [{"le_id": "grondwerker-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "koelie-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}, {"le_id": "loonslaaf-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "pejorative", "domain": null}}], "odwn-10-101160806-n": [{"le_id": "koelie-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}], "odwn-10-100082478-n": [{"le_id": "kaffer-n-2", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": "offensive", "domain": null}}], "odwn-10-101546688-n": [{"le_id": "allochtoon-n-1", "pragmatics": {"register": null, "geography": null, "chronology": null, "connotation": null, "domain": null}}]} \ No newline at end of file diff --git a/sensitivity_markers/explicit/pwn_explicit.csv b/sensitivity_markers/explicit/pwn_explicit.csv new file mode 100644 index 0000000..b6913ad --- /dev/null +++ b/sensitivity_markers/explicit/pwn_explicit.csv @@ -0,0 +1,31 @@ +,resource,lang,lemma,entity_id,explicit_marker,value,level +0,pwn,en,headhunter,headhunter.n.01,usage_domain,['colloquialism.n.01'],1 +1,pwn,en,indian,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +2,pwn,en,coolie,coolie.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",3 +3,pwn,en,white,white-shoe.s.01,usage_domain,['colloquialism.n.01'],1 +4,pwn,en,white,white_trash.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +5,pwn,en,white,whitey.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +6,pwn,en,caucasian,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +7,pwn,en,kaffir,kaffir.n.02,usage_domain,['disparagement.n.01'],3 +8,pwn,en,descent,chink.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +9,pwn,en,descent,paddy.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +10,pwn,en,descent,wop.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +11,pwn,en,descent,jap.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +12,pwn,en,descent,spic.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01', 'slang.n.02']",1 +13,pwn,en,descent,greaser.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +14,pwn,en,descent,kraut.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +15,pwn,en,mongoloid,mongoloid.n.02,usage_domain,['disparagement.n.01'],3 +16,pwn,en,mongoloid,mongoloid.a.03,usage_domain,['disparagement.n.01'],3 +17,pwn,en,homosexual,butch.s.02,usage_domain,['slang.n.02'],2 +18,pwn,en,homosexual,straight.s.10,usage_domain,['colloquialism.n.01'],1 +19,pwn,en,homosexual,fagot.n.01,usage_domain,['disparagement.n.01'],3 +20,pwn,en,native,redskin.n.01,usage_domain,"['disparagement.n.01', 'slang.n.02']",1 +21,pwn,en,black,kaffir.n.02,usage_domain,['disparagement.n.01'],3 +22,pwn,en,black,mammy.n.01,usage_domain,['disparagement.n.01'],1 +23,pwn,en,black,pickaninny.n.01,usage_domain,"['disparagement.n.01', 'ethnic_slur.n.01']",1 +24,pwn,en,queer,fagot.n.01,usage_domain,['disparagement.n.01'],3 +25,pwn,en,queer,fishy.s.02,usage_domain,['colloquialism.n.01'],2 +26,pwn,en,half-breed,half-breed.n.01,usage_domain,['disparagement.n.01'],3 +27,pwn,en,lilliputian,fiddling.s.01,usage_domain,['colloquialism.n.01'],2 +28,pwn,en,race,pumped-up.s.01,usage_domain,['colloquialism.n.01'],1 +29,pwn,en,race,burnup.n.01,usage_domain,['slang.n.02'],1 diff --git a/sensitivity_markers/explicit/wd_explicit.csv b/sensitivity_markers/explicit/wd_explicit.csv new file mode 100644 index 0000000..b6b4f08 --- /dev/null +++ b/sensitivity_markers/explicit/wd_explicit.csv @@ -0,0 +1,89 @@ +,resource,lang,lemma,entity_id,explicit_marker,value,level +0,wikidata,en,immigrant,Q1532765,P31,Q1371427,1 +1,wikidata,en,immigrant,Q55611664,P31,Q545779,1 +2,wikidata,en,barbarian,Q134313,P31,Q1371427,3 +3,wikidata,en,servant,Q10543172,P31,Q16335296,1 +4,wikidata,en,servant,Q1075791,P31,Q16335296,1 +5,wikidata,en,servant,Q303928,P31,Q16335296,1 +6,wikidata,en,servant,Q855855,P31,Q16335296,3 +7,wikidata,en,servant,Q3007620,P31,Q16335296,1 +8,wikidata,en,servant,Q3032660,P31,Q16335296,1 +9,wikidata,en,servant,Q5913718,P31,Q545779,1 +10,wikidata,en,servant,Q1412722,P31,Q16335296,1 +11,wikidata,en,gypsy,Q76475,P31,Q545779,1 +12,wikidata,en,white,Q7129609,P31,Q2042898,3 +13,wikidata,en,white,Q1066801,P31,Q545779,1 +14,wikidata,en,white,Q95530210,P31,Q545779,1 +15,wikidata,en,white,Q1135775,P31,Q545779,1 +16,wikidata,en,white,Q45991,P31,Q1371427,1 +17,wikidata,en,caucasian,Q7129609,P31,Q2042898,3 +18,wikidata,en,kaffir,Q1285250,P31,Q1371427,3 +19,wikidata,en,homosexual,Q165371,P31,Q1520214,1 +20,wikidata,en,page,Q110768064,P2559,add to statements where the number of pages (P1104) has been inferred from the referenced page numbers (P304),1 +21,wikidata,en,page,Q112059263,P2559,Use as the value for statements with property P887,1 +22,wikidata,en,page,Q70894304,P2559,"To clarify that a linked redirect page is intentional or not, a proposal is drafted at Wikidata:Sitelinks to redirects",1 +23,wikidata,en,page,Q21510852,P2559,use as value for P2302 (property constraint),1 +24,wikidata,en,page,Q855855,P31,Q16335296,3 +25,wikidata,en,page,Q3938,P2559,"This is not the actual sandbox of Wikidata. For test editing, use Q4115189, Q13406268, Q15397819, or Q112795079.",1 +26,wikidata,en,native,Q96200400,P2559,P2283 => Q96200400 (qualifier P642 => [the particular indigenous people(s) acknowledged]),2 +27,wikidata,en,negro,Q1130557,P31,Q1371427,3 +28,wikidata,en,negro,Q5913718,P31,Q545779,1 +29,wikidata,en,negro,Q1974358,P31,Q545779,1 +30,wikidata,en,mulatto,Q191923,P31,Q2042898,3 +31,wikidata,en,aboriginal,Q96200400,P2559,P2283 => Q96200400 (qualifier P642 => [the particular indigenous people(s) acknowledged]),2 +32,wikidata,en,eskimo,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",1 +33,wikidata,en,gay,Q165371,P31,Q1520214,1 +34,wikidata,en,gay,Q898608,P31,Q545779,1 +35,wikidata,en,gay,Q55657493,P31,Q545779,1 +36,wikidata,en,colored,Q67085833,P2559,"use with P1552 to indicate that a vinyl record is anything other than black in color; qualify with P5422, P462 where applicable",1 +37,wikidata,en,inuit,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",1 +38,wikidata,en,black,Q1130557,P31,Q1371427,3 +39,wikidata,en,black,Q1455718,P31,Q1371427,1 +40,wikidata,en,black,Q67085833,P2559,"use with P1552 to indicate that a vinyl record is anything other than black in color; qualify with P5422, P462 where applicable",1 +41,wikidata,en,black,Q1285250,P31,Q1371427,3 +42,wikidata,en,black,Q4117010,P31,Q1371427,1 +43,wikidata,en,black,Q45991,P31,Q1371427,1 +44,wikidata,en,queer,Q51415,P31,Q1520214,3 +45,wikidata,en,ethnic groups,Q106537557,P2559,Generally used when music genre includes the name of an ethnic group,1 +46,wikidata,en,ethnic groups,Q112583744,P2559,created to avoid controversies around the question if French (Q121842) is an ethnic group. This should be an exception. Please don't create items for other ethnic or cultural groups in fiction.,1 +47,wikidata,en,trans,Q15711994,P2559,"This item is about a group of isomers and should be used in items describing a group of chemical entities, not a mixture of chemical entities (isomers)",1 +48,wikidata,en,trans,Q55640599,P2559,"If a given item describes a set of chemical entities of theoretically unlimited number of members (e.g. compounds having a specific functional group or a specified number of rings), then it is a ""structural class of chemical entities"" (Q47154513) or one of its subclasses.",1 +49,wikidata,en,race,Q989255,P2559,for Middle-Earth peoples use Q17412916,1 +50,wikidata,en,primitive,Q134313,P31,Q1371427,3 +51,wikidata,en,retarded,Q18394147,P31,Q22116852,3 +52,wikidata,en,slave,Q10076267,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",1 +53,wikidata,en,slave,Q1617492,P31,Q16335296,2 +54,wikidata,en,slave,Q12773225,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",3 +55,wikidata,en,slave,Q588083,P31,Q16335296,1 +56,wikidata,en,slave,Q4666486,P31,Q545779,1 +57,wikidata,en,ethnicity,Q106537557,P2559,Generally used when music genre includes the name of an ethnic group,1 +58,wikidata,en,ethnicity,Q112078715,P2559,Use as the value for statements with property P887,2 +59,wikidata,en,ethnicity,Q5101084,P31,Q545779,1 +60,wikidata,en,indigenous,Q1285250,P31,Q1371427,3 +61,wikidata,en,indigenous,Q96200400,P2559,P2283 => Q96200400 (qualifier P642 => [the particular indigenous people(s) acknowledged]),2 +62,wikidata,en,indigenous,Q5140747,P31,Q1371427,1 +63,wikidata,en,traditional,Q96200400,P2559,P2283 => Q96200400 (qualifier P642 => [the particular indigenous people(s) acknowledged]),2 +64,wikidata,en,traditional,Q113570992,P31,Q16335296,1 +65,wikidata,nl,homo,Q1975772,P31,Q545779,1 +66,wikidata,nl,homo,Q55657493,P31,Q545779,1 +67,wikidata,nl,jap,Q1192767,P31,Q545779,3 +68,wikidata,nl,neger,Q1130557,P31,Q1371427,3 +69,wikidata,nl,bediende,Q855855,P31,Q16335296,3 +70,wikidata,nl,inuk,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",2 +71,wikidata,nl,homoseksueel,Q165371,P31,Q1520214,1 +72,wikidata,nl,queer,Q51415,P31,Q1520214,3 +73,wikidata,nl,zigeuner,Q76475,P31,Q545779,3 +74,wikidata,nl,zwart,Q1130557,P31,Q1371427,3 +75,wikidata,nl,kaukasisch,Q7129609,P31,Q2042898,3 +76,wikidata,nl,mulat,Q191923,P31,Q2042898,3 +77,wikidata,nl,ras,Q1130557,P31,Q1371427,3 +78,wikidata,nl,ras,Q7129609,P31,Q2042898,3 +79,wikidata,nl,ras,Q989255,P2559,for Middle-Earth peoples use Q17412916,2 +80,wikidata,nl,etnische groep,Q106537557,P2559,Generally used when music genre includes the name of an ethnic group,1 +81,wikidata,nl,etnische groep,Q10969817,P31,Q545779,1 +82,wikidata,nl,barbaar,Q134313,P31,Q1371427,3 +83,wikidata,nl,slaaf,Q12773225,P2559,"Don't use for occupation (P106), instead use social classification (P3716)",3 +84,wikidata,nl,eskimo,Q4532729,P2559,"Nowadays many organizations are using a broader concept ""arctic studies"" instead of ""eskimology"".",2 +85,wikidata,nl,page,Q855855,P31,Q16335296,3 +86,wikidata,nl,kaffer,Q1285250,P31,Q1371427,3 +87,wikidata,nl,wit,Q1135775,P31,Q545779,1 diff --git a/sensitivity_markers/explicit/wikidata_P31_all.csv b/sensitivity_markers/explicit/wikidata_P31_all.csv index 4206417..f39a833 100644 --- a/sensitivity_markers/explicit/wikidata_P31_all.csv +++ b/sensitivity_markers/explicit/wikidata_P31_all.csv @@ -1,4 +1,202 @@ item,instance_of +http://www.wikidata.org/entity/L37606-S1,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/L7015-S3,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/L164494-S1,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/L1044337,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/L1096222,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q76475,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q171751,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q193607,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q193814,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q212452,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q225098,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q252375,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q253506,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q337914,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q356367,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q423621,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q587231,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q631956,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q641593,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q646022,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q704597,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q716885,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q741775,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q749446,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q838191,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q858215,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q898608,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1066801,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1067614,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1135775,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1138434,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1141345,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1192767,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1340226,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1382809,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1455718,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1497835,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1499677,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1503467,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1508980,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1631473,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1688741,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1752720,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1790733,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1797042,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1937101,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1942418,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1964958,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1974358,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1975772,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q1988861,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2165166,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2281589,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2415705,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2460281,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2660346,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q2916314,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3000582,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3050851,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3052630,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3054155,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3066167,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3175821,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3190168,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3195911,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3293600,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3365273,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3433266,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3543660,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q3613936,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4117010,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4308992,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4375149,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4481595,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4666486,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4783473,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4889928,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q4960224,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5089376,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5101084,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5255532,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5365989,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5616647,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5762570,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5764134,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q5913718,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6009200,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6192243,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6206877,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6301005,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6630264,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6785843,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6957303,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q6983868,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7581775,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7737989,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7749836,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7813776,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7832808,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7845194,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7877786,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7972083,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q7984571,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q8017761,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q8025244,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q8190641,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q9340030,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10494351,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10495919,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10516126,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10527388,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10605534,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10883485,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10893757,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q10969817,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11078607,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11263899,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11317694,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11327532,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11502136,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11657351,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q11883526,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12034410,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12154196,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12173790,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12208274,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12315032,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12340673,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12478143,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12618470,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12619367,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q12646345,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q13198392,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q16692308,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q16823819,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q16984810,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17011948,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17050661,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17068081,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17111307,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17112591,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q17130746,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q18973425,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q18986590,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q20825920,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q21070717,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q21088778,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q22833386,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q23018238,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q23043453,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q23719438,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q24965086,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q28679032,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q29093219,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q30315326,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q30598504,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q30602818,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q30603936,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q31821011,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q47005895,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q55611664,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q55630850,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q55657493,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q56661036,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q59604415,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q61838206,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q64102969,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q65045683,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q65229498,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q65303355,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q65794649,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q80996540,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q85865182,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q95530210,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q97352327,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q98968151,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q102112271,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q102931604,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q102947518,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q104563535,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q104787097,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q105554633,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q106434947,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q109017490,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q109391487,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q110442848,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q110898250,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q112659251,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q113126434,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q113621766,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q114829786,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q115651682,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q117538548,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q117803563,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q117871613,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q118324158,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q118611222,http://www.wikidata.org/entity/Q545779 +http://www.wikidata.org/entity/Q120074101,http://www.wikidata.org/entity/Q545779 http://www.wikidata.org/entity/L176804-S1,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/L314481,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/L179585,http://www.wikidata.org/entity/Q1371427 @@ -42,6 +240,7 @@ http://www.wikidata.org/entity/Q2552898,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q2607673,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q2621965,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q3271973,http://www.wikidata.org/entity/Q1371427 +http://www.wikidata.org/entity/Q3394291,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q3676388,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q3735685,http://www.wikidata.org/entity/Q1371427 http://www.wikidata.org/entity/Q3772738,http://www.wikidata.org/entity/Q1371427 diff --git a/sensitivity_markers/explicit/wikidata_explicit_SPARQL.txt b/sensitivity_markers/explicit/wikidata_explicit_SPARQL.txt new file mode 100644 index 0000000..447136e --- /dev/null +++ b/sensitivity_markers/explicit/wikidata_explicit_SPARQL.txt @@ -0,0 +1,16 @@ +SELECT ?item ?instance_of +WHERE +{ + VALUES ?instance_of {wd:Q1371427 wd:Q22116852 wd:Q2042898 wd:Q1520214 wd:Q16335296 wd:Q545779} + ?item wdt:P31 ?instance_of . + +} + +SELECT ?item ?usage_instructions +WHERE +{ + ?item wdt:P2559 ?usage_instructions . + + FILTER (lang(?usage_instructions) = "en" || lang(?usage_instructions) = "nl") + +} \ No newline at end of file diff --git a/sensitivity_markers/implicit/aat_en_implicit.csv b/sensitivity_markers/implicit/aat_en_implicit.csv new file mode 100644 index 0000000..f54782d --- /dev/null +++ b/sensitivity_markers/implicit/aat_en_implicit.csv @@ -0,0 +1,56 @@ +,resource,lang,lemma,entity_id,property,value,implicit_marker,level +0,aat,en,indian,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +1,aat,en,indian,300375580,scopeNote,Family of aquatic plants containing two species. Some authorities consider the two species to constitute a separate order (Nelumbonales) because of important botanical characteristics that suggest a different evolutionary origin from the other water lilies.,consider,1 +2,aat,en,indian,300386675,scopeNote,"Distinctive handbells or gongs, used as an instrument in Indian music and in Buddhist ritual. A ghanta may be paired with a vajra; use the more specific ""vajras-ghantas.""",use the more specific,1 +3,aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +4,aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +5,aat,en,indian,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +6,aat,en,indian,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +7,aat,en,servant,300025874,scopeNote,"Generally in historical usage, for people who are privately employed to perform personal or household services.",historical usage,3 +8,aat,en,hottentot,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +9,aat,en,white,300264417,scopeNote,"A Roman Catholic religious order that originated in the 12th century from hermits on Mount Carmel who sought the way of life of the prophet Elijah. When the Crusades failed, the Carmelites migrated to Europe where they flourished as mendicant friars. Solitude, abstinence, and prayer are strictly practiced. In 1452 the friars were joined by Carmelite nuns (Sisters of the Blessed Virgin Mary of Mt. Carmel), the Carmelite Second Order. The Carmelites do not have a founding figure as do many orders, but they consider Elijah and Mary, both central to Carmelite consciousness, as their founders. Important reform figures are St. Teresa of Avila, reformer of the female order in 1562, and St. John of the Cross, who similarly reformed the male order later in the century. The reformed branch became its own order in 1593 and is referred to as the Discalced Carmelites.",consider,1 +10,aat,en,white,300013940,scopeNote,"Warm yellow pigment containing lead antimonate that has been used as a colorant for glass, ceramic tiles, and paint for at least 3500 years. It is probably named after the its resemblance to the yellow minerals found at Mount Vesuvius near Naples, Italy, although it not well documented that the pigment was first made in Naples. The specific color of the pigment depends on the method and temperature of manufacture. It came into widespread use in the 18th century, replacing lead-tin yellow as the pigment most often used by artists in Europe. The term is also used loosely to refer to other pigments imitating Naples yellow but produced by mixing together pigments such as cadmium yellow, zinc white, ochre, and Venetian red.",specific color of the pigment depends on the method and temperature of manufacture. It came into widespread use,1 +11,aat,en,white,300043246,scopeNote,"In a general sense, refers to all drinking glasses intended for wine, made in various shapes (usually stemmed), sizes, and styles; each is said to be most suitable for a particular type of wine. In a specific sense, the term refers only to glasses intended for use at table for wine to accompany the meal, and excluding champagne glasses and other specialty glasses. In this sense, in a matching set of stemware, the wine glass is smaller than a goblet for water, but larger than glasses for sherry, port wine, or liqueur. In such a set, there may be separate glasses of distinctive form for white and for red wine. For similar but smaller drinking glasses used for serving other beverages, use ""gin glasses"" or another specific term.","specific sense, the term refers only to glasses intended for use at table for wine to accompany the meal, and excluding champagne glasses and other specialty glasses. In this sense, in a matching set of stemware, the wine glass is smaller than a goblet for water, but larger than glasses for sherry, port wine, or liqueur. In such a set, there may be separate glasses of distinctive form for white and for red wine. For similar but smaller drinking glasses used for serving other beverages, use",1 +12,aat,en,descent,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +13,aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +14,aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +15,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",pejorative,3 +16,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead,3 +17,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead the most specific,3 +18,aat,en,native,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +19,aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +20,aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +21,aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +22,aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +23,aat,en,native,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +24,aat,en,native,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +25,aat,en,disabled,300189309,altLabel_comment,term is considered offensive,offensive,2 +26,aat,en,disabled,300025925,altLabel_comment,term is considered offensive,offensive,3 +27,aat,en,western,300264554,scopeNote,"Refers to marks used in Western architecture to identify the mason who carved the stone at his banker in the building lodge. The origins and intended use of banker marks varied through history, and are not entirely understood. Early banker marks were apparently used to assure responsibility and quality control in a large building project where a number of less-skilled masons were employed. By the 13th century, banker marks often identified stones carved by specific task, so that the masons could be paid appropriately. Bankers marks typically appear on the work of masons less skilled than the freemasons, who carved moldings and figures. The banker mark eventually came to identify the mason himself. It was often assumed as a signature outside the context of the building site.","use of banker marks varied through history, and are not entirely understood. Early banker marks were apparently used to assure responsibility and quality control in a large building project where a number of less-skilled masons were employed. By the 13th century, banker marks often identified stones carved by specific",1 +28,aat,en,western,300417418,scopeNote,"Refers to a contemporary fine art trend in the Philippines beginning from the postwar period. It is first used to refer to a group of artists associated with the Philippine Art Gallery (1951-1969) who began to call themselves Neo-Realists in 1949. Realism in this case refers to how these artists used their subjective, internal vision of reality to create works of art. Neo-Realism was formed as a reaction to the perceived academic and sentimental status of art in the previous generation. In a sense it was a seminally representational style that was more open to various degrees of abstraction opened up through increasing familiarity with western modern art movements. Although initially facing disapproval from the public and the established art world, the ideologies and styles of the Neo-Realists soon became accepted and affected the development of Filipino art in the following decades.",call themselves,1 +29,aat,en,aboriginal,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +30,aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +31,aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +32,aat,en,eskimo,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +33,aat,en,hermaphrodite,300386060,scopeNote,"People that are born with both male and female sex organs. Historically the term 'hermaphrodite' has been used in this context, but now prefer 'intersex people'. Reserve use of the term 'hermaphrodite' for the context of organisms that can produce both gametes associated with male and female sexes.",now prefer,3 +34,aat,en,inuit,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +35,aat,en,black,300448122,scopeNote,"Originally, make-up or costume intended to imitate the appearance of a black person, particularly as part of a performance. By extension, any practice of stereotyping dark-skinned people in an exaggerated fashion. Though not exclusive to the United States, blackface was associated with minstrel shows in the US from the 1830s until the mid-20th century; and is widely regarded now as an offensive example of racism. Blackface was adopted by some African American performers in minstrel shows from ca.1840 as a means to earn a living in venues that were otherwise denied them in mainstream show business.",offensive,2 +36,aat,en,black,300265027,scopeNote,"Small, extremely rare egg-shaped vessels of ancient Greece, found in both black- and red-figure. The specific use of oa is not determined although real eggs as well as marble and ceramic ones were placed in graves. Lidded oa might have held scented oil (perfume). Lidless oa were probably not containers since they either have a small hole at one or both end or no opening at all.",specific use,1 +37,aat,en,ethnic groups,300016563,scopeNote,"Style and culture of the Sotho ethnic group, located primarily in Lesotho. They were originally united by a common loyalty to the royal house of Moshoeshoe I, who founded the Sotho nation in the 19th century. For the cultures of the African people living in southern Africa who speak or who are descendants of those who traditionally spoke the Sesotho or Southern Sotho language, use the more specific ""Southern Sotho.""",use the more specific,1 +38,aat,en,ethnic groups,300016563,altLabel_comment,"for the more specific culture of those who speak Sesotho, use ""Southern Sotho""","specific culture of those who speak Sesotho, use",1 +39,aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",pejorative,3 +40,aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",consider,3 +41,aat,en,race,300379167,scopeNote,"Tournaments in which knights, divided into companies (quadrilles) and distinguished by liveries, are engaged in various plays and exercises; to this were often added chariot races, and other shows and entertainments. For specific tournaments, races, or balletic exercises involving horses, use ""equestrian ballet"" or ""horse races.""","specific tournaments, races, or balletic exercises involving horses, use",1 +42,aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +43,aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +44,aat,en,primitive,300265683,scopeNote,"Phylum of primitive multicellular aquatic animals. There are approximately 5,000 described species and inhabit all seas, where they occur attached to surfaces from the intertidal zone to depths of 29,000 feet or more. Early naturalists regarded the sponges as plants because of their frequent branching form and their lack of obvious movement. The animal nature of sponges was first described in 1755, and was confirmed in 1765 after observations revealed movement of their openings. In structure, function, and development, however, sponges are distinct from other animals. Many zoologists regard sponges as occupying an isolated position in the animal kingdom and classify them in the subkingdom Parazoa. Other sources consider sponges relatives of the invertebrate animal group coelenterates. Aquatic, chiefly marine animals of the phylum Porifera, varying greatly in size, shape, and color, and having a porous body and siliceous or calcareous internal framework, living permanently attached singly or in groups, feeding b filtering food particles from the water that enters their internal body channels through their pores. They are very simply organized with no mouth, digestive cavity, nerves, muscle, or true behavior, and sometimes are considered to be colonized protozoans rather than single multicellular organisms. For the light, porous, yielding fibrous skeletal matter of these animals, use ""sponge (material).""",consider,2 +45,aat,en,primitive,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +46,aat,en,retarded,300025925,altLabel_comment,term is considered offensive,offensive,3 +47,aat,en,first world,300449024,scopeNote,"Describes nations of the world that are considered economically and technologically advanced. Generally consider this more current and accurate than ""First World.""",consider,3 +48,aat,en,primitivism,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +49,aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +50,aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +51,aat,en,indigenous,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +52,aat,en,tribe,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +53,aat,en,tribe,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +54,aat,en,tribe,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 diff --git a/sensitivity_markers/implicit/aat_implicit.csv b/sensitivity_markers/implicit/aat_implicit.csv new file mode 100644 index 0000000..5194faf --- /dev/null +++ b/sensitivity_markers/implicit/aat_implicit.csv @@ -0,0 +1,72 @@ +,Unnamed: 0,resource,lang,lemma,entity_id,property,value,implicit_marker,level +0,0,aat,en,indian,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +1,1,aat,en,indian,300375580,scopeNote,Family of aquatic plants containing two species. Some authorities consider the two species to constitute a separate order (Nelumbonales) because of important botanical characteristics that suggest a different evolutionary origin from the other water lilies.,consider,1 +2,2,aat,en,indian,300386675,scopeNote,"Distinctive handbells or gongs, used as an instrument in Indian music and in Buddhist ritual. A ghanta may be paired with a vajra; use the more specific ""vajras-ghantas.""",use the more specific,1 +3,3,aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +4,4,aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +5,5,aat,en,indian,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +6,6,aat,en,indian,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +7,7,aat,en,servant,300025874,scopeNote,"Generally in historical usage, for people who are privately employed to perform personal or household services.",historical usage,3 +8,8,aat,en,hottentot,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +9,9,aat,en,white,300264417,scopeNote,"A Roman Catholic religious order that originated in the 12th century from hermits on Mount Carmel who sought the way of life of the prophet Elijah. When the Crusades failed, the Carmelites migrated to Europe where they flourished as mendicant friars. Solitude, abstinence, and prayer are strictly practiced. In 1452 the friars were joined by Carmelite nuns (Sisters of the Blessed Virgin Mary of Mt. Carmel), the Carmelite Second Order. The Carmelites do not have a founding figure as do many orders, but they consider Elijah and Mary, both central to Carmelite consciousness, as their founders. Important reform figures are St. Teresa of Avila, reformer of the female order in 1562, and St. John of the Cross, who similarly reformed the male order later in the century. The reformed branch became its own order in 1593 and is referred to as the Discalced Carmelites.",consider,1 +10,10,aat,en,white,300013940,scopeNote,"Warm yellow pigment containing lead antimonate that has been used as a colorant for glass, ceramic tiles, and paint for at least 3500 years. It is probably named after the its resemblance to the yellow minerals found at Mount Vesuvius near Naples, Italy, although it not well documented that the pigment was first made in Naples. The specific color of the pigment depends on the method and temperature of manufacture. It came into widespread use in the 18th century, replacing lead-tin yellow as the pigment most often used by artists in Europe. The term is also used loosely to refer to other pigments imitating Naples yellow but produced by mixing together pigments such as cadmium yellow, zinc white, ochre, and Venetian red.",specific color of the pigment depends on the method and temperature of manufacture. It came into widespread use,1 +11,11,aat,en,white,300043246,scopeNote,"In a general sense, refers to all drinking glasses intended for wine, made in various shapes (usually stemmed), sizes, and styles; each is said to be most suitable for a particular type of wine. In a specific sense, the term refers only to glasses intended for use at table for wine to accompany the meal, and excluding champagne glasses and other specialty glasses. In this sense, in a matching set of stemware, the wine glass is smaller than a goblet for water, but larger than glasses for sherry, port wine, or liqueur. In such a set, there may be separate glasses of distinctive form for white and for red wine. For similar but smaller drinking glasses used for serving other beverages, use ""gin glasses"" or another specific term.","specific sense, the term refers only to glasses intended for use at table for wine to accompany the meal, and excluding champagne glasses and other specialty glasses. In this sense, in a matching set of stemware, the wine glass is smaller than a goblet for water, but larger than glasses for sherry, port wine, or liqueur. In such a set, there may be separate glasses of distinctive form for white and for red wine. For similar but smaller drinking glasses used for serving other beverages, use",1 +12,12,aat,en,descent,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +13,13,aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +14,14,aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +15,15,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",pejorative,3 +16,16,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead,3 +17,17,aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead the most specific,3 +18,18,aat,en,native,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +19,19,aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +20,20,aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +21,21,aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +22,22,aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +23,23,aat,en,native,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +24,24,aat,en,native,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +25,25,aat,en,disabled,300189309,altLabel_comment,term is considered offensive,offensive,2 +26,26,aat,en,disabled,300025925,altLabel_comment,term is considered offensive,offensive,3 +27,27,aat,en,western,300264554,scopeNote,"Refers to marks used in Western architecture to identify the mason who carved the stone at his banker in the building lodge. The origins and intended use of banker marks varied through history, and are not entirely understood. Early banker marks were apparently used to assure responsibility and quality control in a large building project where a number of less-skilled masons were employed. By the 13th century, banker marks often identified stones carved by specific task, so that the masons could be paid appropriately. Bankers marks typically appear on the work of masons less skilled than the freemasons, who carved moldings and figures. The banker mark eventually came to identify the mason himself. It was often assumed as a signature outside the context of the building site.","use of banker marks varied through history, and are not entirely understood. Early banker marks were apparently used to assure responsibility and quality control in a large building project where a number of less-skilled masons were employed. By the 13th century, banker marks often identified stones carved by specific",1 +28,28,aat,en,western,300417418,scopeNote,"Refers to a contemporary fine art trend in the Philippines beginning from the postwar period. It is first used to refer to a group of artists associated with the Philippine Art Gallery (1951-1969) who began to call themselves Neo-Realists in 1949. Realism in this case refers to how these artists used their subjective, internal vision of reality to create works of art. Neo-Realism was formed as a reaction to the perceived academic and sentimental status of art in the previous generation. In a sense it was a seminally representational style that was more open to various degrees of abstraction opened up through increasing familiarity with western modern art movements. Although initially facing disapproval from the public and the established art world, the ideologies and styles of the Neo-Realists soon became accepted and affected the development of Filipino art in the following decades.",call themselves,1 +29,29,aat,en,aboriginal,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +30,30,aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +31,31,aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +32,32,aat,en,eskimo,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +33,33,aat,en,hermaphrodite,300386060,scopeNote,"People that are born with both male and female sex organs. Historically the term 'hermaphrodite' has been used in this context, but now prefer 'intersex people'. Reserve use of the term 'hermaphrodite' for the context of organisms that can produce both gametes associated with male and female sexes.",now prefer,3 +34,34,aat,en,inuit,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +35,35,aat,en,black,300448122,scopeNote,"Originally, make-up or costume intended to imitate the appearance of a black person, particularly as part of a performance. By extension, any practice of stereotyping dark-skinned people in an exaggerated fashion. Though not exclusive to the United States, blackface was associated with minstrel shows in the US from the 1830s until the mid-20th century; and is widely regarded now as an offensive example of racism. Blackface was adopted by some African American performers in minstrel shows from ca.1840 as a means to earn a living in venues that were otherwise denied them in mainstream show business.",offensive,2 +36,36,aat,en,black,300265027,scopeNote,"Small, extremely rare egg-shaped vessels of ancient Greece, found in both black- and red-figure. The specific use of oa is not determined although real eggs as well as marble and ceramic ones were placed in graves. Lidded oa might have held scented oil (perfume). Lidless oa were probably not containers since they either have a small hole at one or both end or no opening at all.",specific use,1 +37,37,aat,en,ethnic groups,300016563,scopeNote,"Style and culture of the Sotho ethnic group, located primarily in Lesotho. They were originally united by a common loyalty to the royal house of Moshoeshoe I, who founded the Sotho nation in the 19th century. For the cultures of the African people living in southern Africa who speak or who are descendants of those who traditionally spoke the Sesotho or Southern Sotho language, use the more specific ""Southern Sotho.""",use the more specific,1 +38,38,aat,en,ethnic groups,300016563,altLabel_comment,"for the more specific culture of those who speak Sesotho, use ""Southern Sotho""","specific culture of those who speak Sesotho, use",1 +39,39,aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",pejorative,3 +40,40,aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",consider,3 +41,41,aat,en,race,300379167,scopeNote,"Tournaments in which knights, divided into companies (quadrilles) and distinguished by liveries, are engaged in various plays and exercises; to this were often added chariot races, and other shows and entertainments. For specific tournaments, races, or balletic exercises involving horses, use ""equestrian ballet"" or ""horse races.""","specific tournaments, races, or balletic exercises involving horses, use",1 +42,42,aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +43,43,aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +44,44,aat,en,primitive,300265683,scopeNote,"Phylum of primitive multicellular aquatic animals. There are approximately 5,000 described species and inhabit all seas, where they occur attached to surfaces from the intertidal zone to depths of 29,000 feet or more. Early naturalists regarded the sponges as plants because of their frequent branching form and their lack of obvious movement. The animal nature of sponges was first described in 1755, and was confirmed in 1765 after observations revealed movement of their openings. In structure, function, and development, however, sponges are distinct from other animals. Many zoologists regard sponges as occupying an isolated position in the animal kingdom and classify them in the subkingdom Parazoa. Other sources consider sponges relatives of the invertebrate animal group coelenterates. Aquatic, chiefly marine animals of the phylum Porifera, varying greatly in size, shape, and color, and having a porous body and siliceous or calcareous internal framework, living permanently attached singly or in groups, feeding b filtering food particles from the water that enters their internal body channels through their pores. They are very simply organized with no mouth, digestive cavity, nerves, muscle, or true behavior, and sometimes are considered to be colonized protozoans rather than single multicellular organisms. For the light, porous, yielding fibrous skeletal matter of these animals, use ""sponge (material).""",consider,2 +45,45,aat,en,primitive,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +46,46,aat,en,retarded,300025925,altLabel_comment,term is considered offensive,offensive,3 +47,47,aat,en,first world,300449024,scopeNote,"Describes nations of the world that are considered economically and technologically advanced. Generally consider this more current and accurate than ""First World.""",consider,3 +48,48,aat,en,primitivism,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +49,49,aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +50,50,aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +51,51,aat,en,indigenous,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +52,52,aat,en,tribe,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +53,53,aat,en,tribe,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +54,54,aat,en,tribe,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +55,0,aat,nl,indiaan,300017650,scopeNote,"Verwijst naar de cultuur van de Sioux, een indiaans volk (of confederatie van volken) dat op de Noord-Amerikaanse prairie woont en behoort tot de Sioux-taalgroep. Sioux is een afkorting van Nadouessioux, een naam die oorspronkelijk door de Ojibwa werd gebruikt om zichzelf aan te duiden; het woord Dakota betekent ‘bondgenoten’. Er bestonden drie hoofddivisies van de Sioux: Santee, Yankton en Teton, die zichzelf respectievelijk Dakota, Nakota en Lakota noemden.",zichzelf aan te duiden,2 +56,1,aat,nl,indiaan,300016773,scopeNote,"Verwijst naar een taalgroep van Noord-Amerikaanse indianen die tal van linguïstische subgroepen en culturele groepen omvat. Deze willekeurige benaming, afgeleid van het Athabaska-meer, werd in 1836 bedacht door Albert Gallatin als verwijzing naar een cultuur die volgens hem zijn centrum in dit gebied had. Mensen die behoren tot de Athabaskan-taalgroep bevolken grote delen van het subarctisch gebied, alsmede delen van New Mexico en Arizona. De term kent nogal wat spellingsvarianten, die soms zelfs binnen één bron worden gebruikt. De term 'Athapaskan' wordt sinds 1930 algemeen gebruikt. De leden van de groep duiden zichzelf aan als 'Dene' of 'Na-Dené'. Deze term wordt soms als synoniem voor Athapaskan gebruikt, hoewel er soms ook mee wordt verwezen naar een bredere categorie die tevens de Tlingit- en Haida-taalgroepen omvat.",duiden zichzelf,2 +57,2,aat,nl,indiaan,300411107,scopeNote,"Cultuur van de talrijkste groep indianen in Zuid-Amerika. Ze leven in de Centrale Vallei van Chili, ten zuiden van de rivier de Biobío. Een kleinere groep leeft in de provincie Neuquén, in het middenwesten van Argentinië. Vroeger werden de Mapuche door Spaanse etnografen gezien als een van de drie groepen Araukaniërs, waarbij de Picunche en Huillich de andere twee waren. Alle Araukaniërs noemen zichzelf nu Mapuche. In de pre-Spaanse periode leefden de Mapuche verspreid in boerendorpen in de hele Centrale Vallei. Elke nederzetting had een cacique, of hoofd, die meestal alleen in zijn eigen dorp gezag had. De Mapuche verbouwden maïs, bonen, pompoen, aardappelen, chilipepers en andere groenten en leefden verder van visvangst, jacht en het houden van cavia's voor het vlees.",noemen zichzelf,1 +58,3,aat,nl,stam,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +59,4,aat,nl,stam,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 +60,5,aat,nl,stam,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +61,6,aat,nl,traditioneel,300264737,scopeNote,"Verwijst naar schilderijen, beeldhouwwerken, grafische kunst en architectuur die in het recente verleden of het heden zijn vervaardigd. Het verschil met moderne kunst is dat de term 'hedendaagse kunst' niet de betekenis van een niet-traditionele stijl in zich draagt, maar uitsluitend verwijst naar de periode waarin een werk is gemaakt. De begrippen 'modern' en 'hedendaags' zijn dan ook impliciet aan verandering onderhevig. Het woord 'hedendaags' wordt soms in specifiekere zin gebruikt om de kunst tussen circa 1960 of 1970 tot het heden aan te duiden. Om de huidige tijdsperiode aan te duiden zonder relatie tot een kunststijl, gebruik 'hedendaags (generieke tijdsspanne)'.","specifiekere zin gebruikt om de kunst tussen circa 1960 of 1970 tot het heden aan te duiden. Om de huidige tijdsperiode aan te duiden zonder relatie tot een kunststijl, gebruik",1 +62,7,aat,nl,primitief,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +63,8,aat,nl,primitief,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +64,9,aat,nl,pygmee,300016430,scopeNote,"Te gebruiken om werken te beschrijven van bepaalde Afrikaanse volkeren die leven in Kameroen, Equatoriaal-Guinea, de Democratische Republiek Congo, Congo, de Centraal-Afrikaanse Republiek, Rwanda en Burundi. De term Pygmee heeft soms een negatieve bijklank. Waar mogelijk verdient het gebruik van de specifieke naam van een subgroep de voorkeur.",negatieve bijklank,3 +65,10,aat,nl,gekleurd,300266377,scopeNote,"Verwijst in specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik was. Het bedoelde effect is dat van een schilderij op glas. Een albuminedruk wordt gehecht aan een gebogen stuk glas en het papier aan de achterzijde wordt tot aan de emulsielaag weggeschuurd. Dan wordt er een laagje olie aangebracht om het geheel doorschijnend te maken, waarna op de achterzijde de kleuren in detail worden aangebracht. Na het drogen wordt een tweede laag gebogen glas toegevoegd en met kleuren in brede banen beschilderd. Daarachter wordt een laag wit materiaal bevestigd, waarna het geheel aan elkaar wordt gelijmd. Het glas, de oplossingen en de kleefmiddelen waren tot aan de Eerste Wereldoorlog vrij in de handel verkrijgbaar. Het procedé was gebaseerd op 18de-eeuwse met de hand gekleurde gravures, de zogeheten mezzotintschilderijen.","specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik",1 +66,11,aat,nl,primitivisme,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +67,12,aat,nl,wit,300266377,scopeNote,"Verwijst in specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik was. Het bedoelde effect is dat van een schilderij op glas. Een albuminedruk wordt gehecht aan een gebogen stuk glas en het papier aan de achterzijde wordt tot aan de emulsielaag weggeschuurd. Dan wordt er een laagje olie aangebracht om het geheel doorschijnend te maken, waarna op de achterzijde de kleuren in detail worden aangebracht. Na het drogen wordt een tweede laag gebogen glas toegevoegd en met kleuren in brede banen beschilderd. Daarachter wordt een laag wit materiaal bevestigd, waarna het geheel aan elkaar wordt gelijmd. Het glas, de oplossingen en de kleefmiddelen waren tot aan de Eerste Wereldoorlog vrij in de handel verkrijgbaar. Het procedé was gebaseerd op 18de-eeuwse met de hand gekleurde gravures, de zogeheten mezzotintschilderijen.","specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik",1 +68,13,aat,nl,inheems,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +69,14,aat,nl,inheems,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +70,15,aat,nl,inheems,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 diff --git a/sensitivity_markers/implicit/aat_nl_implicit.csv b/sensitivity_markers/implicit/aat_nl_implicit.csv new file mode 100644 index 0000000..9c1eaa8 --- /dev/null +++ b/sensitivity_markers/implicit/aat_nl_implicit.csv @@ -0,0 +1,17 @@ +,resource,lang,lemma,entity_id,property,value,implicit_marker,level +0,aat,nl,indiaan,300017650,scopeNote,"Verwijst naar de cultuur van de Sioux, een indiaans volk (of confederatie van volken) dat op de Noord-Amerikaanse prairie woont en behoort tot de Sioux-taalgroep. Sioux is een afkorting van Nadouessioux, een naam die oorspronkelijk door de Ojibwa werd gebruikt om zichzelf aan te duiden; het woord Dakota betekent ‘bondgenoten’. Er bestonden drie hoofddivisies van de Sioux: Santee, Yankton en Teton, die zichzelf respectievelijk Dakota, Nakota en Lakota noemden.",zichzelf aan te duiden,2 +1,aat,nl,indiaan,300016773,scopeNote,"Verwijst naar een taalgroep van Noord-Amerikaanse indianen die tal van linguïstische subgroepen en culturele groepen omvat. Deze willekeurige benaming, afgeleid van het Athabaska-meer, werd in 1836 bedacht door Albert Gallatin als verwijzing naar een cultuur die volgens hem zijn centrum in dit gebied had. Mensen die behoren tot de Athabaskan-taalgroep bevolken grote delen van het subarctisch gebied, alsmede delen van New Mexico en Arizona. De term kent nogal wat spellingsvarianten, die soms zelfs binnen één bron worden gebruikt. De term 'Athapaskan' wordt sinds 1930 algemeen gebruikt. De leden van de groep duiden zichzelf aan als 'Dene' of 'Na-Dené'. Deze term wordt soms als synoniem voor Athapaskan gebruikt, hoewel er soms ook mee wordt verwezen naar een bredere categorie die tevens de Tlingit- en Haida-taalgroepen omvat.",duiden zichzelf,2 +2,aat,nl,indiaan,300411107,scopeNote,"Cultuur van de talrijkste groep indianen in Zuid-Amerika. Ze leven in de Centrale Vallei van Chili, ten zuiden van de rivier de Biobío. Een kleinere groep leeft in de provincie Neuquén, in het middenwesten van Argentinië. Vroeger werden de Mapuche door Spaanse etnografen gezien als een van de drie groepen Araukaniërs, waarbij de Picunche en Huillich de andere twee waren. Alle Araukaniërs noemen zichzelf nu Mapuche. In de pre-Spaanse periode leefden de Mapuche verspreid in boerendorpen in de hele Centrale Vallei. Elke nederzetting had een cacique, of hoofd, die meestal alleen in zijn eigen dorp gezag had. De Mapuche verbouwden maïs, bonen, pompoen, aardappelen, chilipepers en andere groenten en leefden verder van visvangst, jacht en het houden van cavia's voor het vlees.",noemen zichzelf,1 +3,aat,nl,stam,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +4,aat,nl,stam,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 +5,aat,nl,stam,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +6,aat,nl,traditioneel,300264737,scopeNote,"Verwijst naar schilderijen, beeldhouwwerken, grafische kunst en architectuur die in het recente verleden of het heden zijn vervaardigd. Het verschil met moderne kunst is dat de term 'hedendaagse kunst' niet de betekenis van een niet-traditionele stijl in zich draagt, maar uitsluitend verwijst naar de periode waarin een werk is gemaakt. De begrippen 'modern' en 'hedendaags' zijn dan ook impliciet aan verandering onderhevig. Het woord 'hedendaags' wordt soms in specifiekere zin gebruikt om de kunst tussen circa 1960 of 1970 tot het heden aan te duiden. Om de huidige tijdsperiode aan te duiden zonder relatie tot een kunststijl, gebruik 'hedendaags (generieke tijdsspanne)'.","specifiekere zin gebruikt om de kunst tussen circa 1960 of 1970 tot het heden aan te duiden. Om de huidige tijdsperiode aan te duiden zonder relatie tot een kunststijl, gebruik",1 +7,aat,nl,primitief,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +8,aat,nl,primitief,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +9,aat,nl,pygmee,300016430,scopeNote,"Te gebruiken om werken te beschrijven van bepaalde Afrikaanse volkeren die leven in Kameroen, Equatoriaal-Guinea, de Democratische Republiek Congo, Congo, de Centraal-Afrikaanse Republiek, Rwanda en Burundi. De term Pygmee heeft soms een negatieve bijklank. Waar mogelijk verdient het gebruik van de specifieke naam van een subgroep de voorkeur.",negatieve bijklank,3 +10,aat,nl,gekleurd,300266377,scopeNote,"Verwijst in specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik was. Het bedoelde effect is dat van een schilderij op glas. Een albuminedruk wordt gehecht aan een gebogen stuk glas en het papier aan de achterzijde wordt tot aan de emulsielaag weggeschuurd. Dan wordt er een laagje olie aangebracht om het geheel doorschijnend te maken, waarna op de achterzijde de kleuren in detail worden aangebracht. Na het drogen wordt een tweede laag gebogen glas toegevoegd en met kleuren in brede banen beschilderd. Daarachter wordt een laag wit materiaal bevestigd, waarna het geheel aan elkaar wordt gelijmd. Het glas, de oplossingen en de kleefmiddelen waren tot aan de Eerste Wereldoorlog vrij in de handel verkrijgbaar. Het procedé was gebaseerd op 18de-eeuwse met de hand gekleurde gravures, de zogeheten mezzotintschilderijen.","specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik",1 +11,aat,nl,primitivisme,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +12,aat,nl,wit,300266377,scopeNote,"Verwijst in specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik was. Het bedoelde effect is dat van een schilderij op glas. Een albuminedruk wordt gehecht aan een gebogen stuk glas en het papier aan de achterzijde wordt tot aan de emulsielaag weggeschuurd. Dan wordt er een laagje olie aangebracht om het geheel doorschijnend te maken, waarna op de achterzijde de kleuren in detail worden aangebracht. Na het drogen wordt een tweede laag gebogen glas toegevoegd en met kleuren in brede banen beschilderd. Daarachter wordt een laag wit materiaal bevestigd, waarna het geheel aan elkaar wordt gelijmd. Het glas, de oplossingen en de kleefmiddelen waren tot aan de Eerste Wereldoorlog vrij in de handel verkrijgbaar. Het procedé was gebaseerd op 18de-eeuwse met de hand gekleurde gravures, de zogeheten mezzotintschilderijen.","specifieke zin naar foto's die zijn gemaakt op basis van een met de hand gekleurd positief beeldprocedé, zoals dat vanaf de jaren 80 van de 19de eeuw tot en met 1920 in gebruik",1 +13,aat,nl,inheems,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +14,aat,nl,inheems,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +15,aat,nl,inheems,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 diff --git a/sensitivity_markers/implicit/excluded_implicit_markers.txt b/sensitivity_markers/implicit/excluded_implicit_markers.txt new file mode 100644 index 0000000..8eaf575 --- /dev/null +++ b/sensitivity_markers/implicit/excluded_implicit_markers.txt @@ -0,0 +1,74 @@ +excluded implicit markers after manual check + +AAT + +300375580 +300264417 +300013940 +300043246 +300264554 +300265027 +300379167 +300265683 +300264737 +300266377 +300266377 + +PWN + +ellis_island.n.01 +left-handed.s.02 +potlatch.n.01 +quechua.n.02 +arapaho.n.01 +caddo.n.01 +colorado_river_hemp.n.01 +atakapa.n.01 +chimariko.n.01 +iroquois.n.01 +mohave.n.01 +quechua.n.01 +soma.n.01 +boskop_man.n.01 +fox_terrier.n.01 +bernese_mountain_dog.n.01 +theurgy.n.02 +hunkpapa.n.01 +dita.n.01 +ivory_tree.n.01 +boneset.n.02 +common_milkwort.n.01 +whale_oil.n.01 +great_plains.n.01 +giant_buttercup.n.01 +catharanthus.n.01 +coltsfoot.n.02 +common_thyme.n.01 +habenaria.n.01 +madder.n.01 +sea_holly.n.01 +cynancum.n.01 +benin.n.01 +togo.n.01 +aachen.n.01 +croatia.n.01 +burkina_faso.n.01 +guinea.n.03 +hejaz.n.01 +klaipeda.n.01 +erie.n.01 +hidatsa.n.01 +hunkpapa.n.01 +oglala.n.01 +ingrian.n.01 +calocedrus.n.01 +gumweed.n.01 +common_thyme.n.01 +fox_terrier.n.01 +bernese_mountain_dog.n.01 +georgia.n.03 +oglala.n.01 +arrow_wood.n.02 +monera.n.01 +homo_soloensis.n.01 +arapaho.n.01 \ No newline at end of file diff --git a/sensitivity_markers/implicit/implicit_all.csv b/sensitivity_markers/implicit/implicit_all.csv new file mode 100644 index 0000000..a45789f --- /dev/null +++ b/sensitivity_markers/implicit/implicit_all.csv @@ -0,0 +1,198 @@ +resource,lang,lemma,entity_id,property,value,implicit_marker,level +aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",pejorative,3 +aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead,3 +aat,en,pygmy,300016430,scopeNote,"The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of ""Pygmy"" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.",use instead the most specific,3 +aat,nl,pygmee,300016430,scopeNote,"Te gebruiken om werken te beschrijven van bepaalde Afrikaanse volkeren die leven in Kameroen, Equatoriaal-Guinea, de Democratische Republiek Congo, Congo, de Centraal-Afrikaanse Republiek, Rwanda en Burundi. De term Pygmee heeft soms een negatieve bijklank. Waar mogelijk verdient het gebruik van de specifieke naam van een subgroep de voorkeur.",negatieve bijklank,3 +aat,en,ethnic groups,300016563,scopeNote,"Style and culture of the Sotho ethnic group, located primarily in Lesotho. They were originally united by a common loyalty to the royal house of Moshoeshoe I, who founded the Sotho nation in the 19th century. For the cultures of the African people living in southern Africa who speak or who are descendants of those who traditionally spoke the Sesotho or Southern Sotho language, use the more specific ""Southern Sotho.""",use the more specific,1 +aat,en,ethnic groups,300016563,altLabel_comment,"for the more specific culture of those who speak Sesotho, use ""Southern Sotho""","specific culture of those who speak Sesotho, use",1 +aat,en,hottentot,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +aat,en,descent,300016575,altLabel_comment,"now considered pejorative, used after 1652/mid-20th century; probably invented by the Dutch colonists in imitation of the clicking sounds of their language",pejorative,3 +aat,nl,indiaan,300016773,scopeNote,"Verwijst naar een taalgroep van Noord-Amerikaanse indianen die tal van linguïstische subgroepen en culturele groepen omvat. Deze willekeurige benaming, afgeleid van het Athabaska-meer, werd in 1836 bedacht door Albert Gallatin als verwijzing naar een cultuur die volgens hem zijn centrum in dit gebied had. Mensen die behoren tot de Athabaskan-taalgroep bevolken grote delen van het subarctisch gebied, alsmede delen van New Mexico en Arizona. De term kent nogal wat spellingsvarianten, die soms zelfs binnen één bron worden gebruikt. De term 'Athapaskan' wordt sinds 1930 algemeen gebruikt. De leden van de groep duiden zichzelf aan als 'Dene' of 'Na-Dené'. Deze term wordt soms als synoniem voor Athapaskan gebruikt, hoewel er soms ook mee wordt verwezen naar een bredere categorie die tevens de Tlingit- en Haida-taalgroepen omvat.",duiden zichzelf,2 +aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +aat,en,indian,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +aat,en,mongoloid,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +aat,en,native,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +aat,en,eskimo,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",now prefer,3 +aat,en,indigenous,300017437,scopeNote,"Whenever possible, use the specific tribal name. The general term ""Native American"" is widely used in the United States, but many groups now prefer ""American Indian"" or ""Indigenous American."" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term ""First Nations."" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use ""Amerindian (culture).""",use the specific,3 +aat,en,native,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +aat,en,eskimo,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +aat,en,inuit,300017447,scopeNote,"Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as ""Chugach,"" ""Inuit,"" or ""Katladlit.""","specific native peoples of the present, use",3 +aat,en,indian,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +aat,en,tribe,300017547,scopeNote,"Refers to the artwork produced by any member of the North American Indian tribes speaking a language of the Iroquoian family, notably the Cayuga, Cherokee, Huron, Mohawk, Oneida, Onondaga, Seneca, and Tuscarora, in addition to the Iroquois proper. The name Iroquois is a French derivation of Irinakhoiw, meaning ""rattlesnakes."" They call themselves Hodenosaunee, meaning ""people of the longhouse."" The Iroquoian linguistic groups occupied a continuous territory around Lakes Ontario, Huron, and Erie, in present-day New York state and Pennsylvania and southern Ontario and Quebec.",call themselves,1 +aat,nl,indiaan,300017650,scopeNote,"Verwijst naar de cultuur van de Sioux, een indiaans volk (of confederatie van volken) dat op de Noord-Amerikaanse prairie woont en behoort tot de Sioux-taalgroep. Sioux is een afkorting van Nadouessioux, een naam die oorspronkelijk door de Ojibwa werd gebruikt om zichzelf aan te duiden; het woord Dakota betekent ‘bondgenoten’. Er bestonden drie hoofddivisies van de Sioux: Santee, Yankton en Teton, die zichzelf respectievelijk Dakota, Nakota en Lakota noemden.",zichzelf aan te duiden,2 +aat,en,servant,300025874,scopeNote,"Generally in historical usage, for people who are privately employed to perform personal or household services.",historical usage,3 +aat,en,disabled,300025925,altLabel_comment,term is considered offensive,offensive,3 +aat,en,retarded,300025925,altLabel_comment,term is considered offensive,offensive,3 +aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +aat,en,native,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",outdated designation,2 +aat,en,primitive,300056460,scopeNote,"An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as ""vernacular architecture,"" or use the most specific name known for the culture of origin.",use the most specific,2 +aat,nl,stam,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +aat,nl,primitief,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +aat,nl,inheems,300056460,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor de architectuur van bepaalde personen die werden beschouwd als buitenstaanders van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen gaat. Gebruik in plaats daarvan andere termen zoals 'inheemse architectuur', of gebruik de meest specifieke benaming voor de cultuur of herkomst die bekend is.",verouderde benaming,2 +aat,en,native,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +aat,en,primitive,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +aat,en,primitivism,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +aat,en,indigenous,300056500,scopeNote,"An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead ""indigenous art,"" ""tribal art,"" or the most specific name known for the culture of origin. Distinct from ""primitivism,"" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.",outdated designation,3 +aat,nl,stam,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +aat,nl,primitief,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +aat,nl,primitivisme,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +aat,nl,inheems,300056500,scopeNote,"Een verouderde benaming die vroeger gebruikt werd voor kunst van bepaald personen die als buitenstaanders werden beschouwd van andere, politiek overheersende culturele groepen; werd voornamelijk gebruikt met betrekking tot bevolkingsgroepen afkomstig uit het gebied ten zuiden van de Sahara, de eilanden in de Stille Oceaan en de inheemse Noord- en Zuid-Amerikaanse stammen. Gebruik in plaats daarvan de meest specifieke benaming van de cultuur of herkomst die bekend is. Te onderscheiden van 'primitivisme', een term die wordt gebruikt voor artistieke stijlen of stromingen die bedoeld zijn om, vaak op romantische of sentimentele wijze, het uiterlijk na te bootsen van kunstvormen die daarvoor als primitief werden bestempeld en andere kunst, geproduceerd door kunstenaars die buiten de grote kunstmarkten werken.",verouderde benaming,2 +aat,en,disabled,300189309,altLabel_comment,term is considered offensive,offensive,2 +aat,en,indian,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +aat,en,native,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +aat,en,tribe,300249545,scopeNote,"Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.",use a more specific,2 +aat,en,hermaphrodite,300386060,scopeNote,"People that are born with both male and female sex organs. Historically the term 'hermaphrodite' has been used in this context, but now prefer 'intersex people'. Reserve use of the term 'hermaphrodite' for the context of organisms that can produce both gametes associated with male and female sexes.",now prefer,3 +aat,en,indian,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +aat,en,aboriginal,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +aat,en,tribe,300386485,scopeNote,"Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.",call themselves,2 +aat,nl,stam,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 +aat,nl,inheems,300386485,scopeNote,"Stijl en cultuur van een van de grootste Indiase geregistreerde stammen, een inheems volk uit de regio Choṭa Nāgpur in de Indiase deelstaat Bihar. Ze noemen zichzelf Kurukh. Vroeger woonden ze verder naar het zuidwesten op het Rohtasplateau, maar ze zijn door andere volkeren verdreven en vertrokken naar Choṭa Nāgpur, waar ze zich vestigden in de nabijheid van Munda-sprekende stammen.",noemen zichzelf,2 +aat,en,indian,300386675,scopeNote,"Distinctive handbells or gongs, used as an instrument in Indian music and in Buddhist ritual. A ghanta may be paired with a vajra; use the more specific ""vajras-ghantas.""",use the more specific,1 +aat,nl,indiaan,300411107,scopeNote,"Cultuur van de talrijkste groep indianen in Zuid-Amerika. Ze leven in de Centrale Vallei van Chili, ten zuiden van de rivier de Biobío. Een kleinere groep leeft in de provincie Neuquén, in het middenwesten van Argentinië. Vroeger werden de Mapuche door Spaanse etnografen gezien als een van de drie groepen Araukaniërs, waarbij de Picunche en Huillich de andere twee waren. Alle Araukaniërs noemen zichzelf nu Mapuche. In de pre-Spaanse periode leefden de Mapuche verspreid in boerendorpen in de hele Centrale Vallei. Elke nederzetting had een cacique, of hoofd, die meestal alleen in zijn eigen dorp gezag had. De Mapuche verbouwden maïs, bonen, pompoen, aardappelen, chilipepers en andere groenten en leefden verder van visvangst, jacht en het houden van cavia's voor het vlees.",noemen zichzelf,1 +aat,en,western,300417418,scopeNote,"Refers to a contemporary fine art trend in the Philippines beginning from the postwar period. It is first used to refer to a group of artists associated with the Philippine Art Gallery (1951-1969) who began to call themselves Neo-Realists in 1949. Realism in this case refers to how these artists used their subjective, internal vision of reality to create works of art. Neo-Realism was formed as a reaction to the perceived academic and sentimental status of art in the previous generation. In a sense it was a seminally representational style that was more open to various degrees of abstraction opened up through increasing familiarity with western modern art movements. Although initially facing disapproval from the public and the established art world, the ideologies and styles of the Neo-Realists soon became accepted and affected the development of Filipino art in the following decades.",call themselves,1 +aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",pejorative,3 +aat,en,maroon,300443390,scopeNote,"Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.",consider,3 +aat,en,black,300448122,scopeNote,"Originally, make-up or costume intended to imitate the appearance of a black person, particularly as part of a performance. By extension, any practice of stereotyping dark-skinned people in an exaggerated fashion. Though not exclusive to the United States, blackface was associated with minstrel shows in the US from the 1830s until the mid-20th century; and is widely regarded now as an offensive example of racism. Blackface was adopted by some African American performers in minstrel shows from ca.1840 as a means to earn a living in venues that were otherwise denied them in mainstream show business.",offensive,2 +aat,en,first world,300449024,scopeNote,"Describes nations of the world that are considered economically and technologically advanced. Generally consider this more current and accurate than ""First World.""",consider,3 +pwn,en,negro,black.n.05,definition,"a person with African ancestry, and are archaic and pejorative today",pejorative,3 +pwn,en,black,black.n.05,definition,"a person with African ancestry, and are archaic and pejorative today",pejorative,3 +pwn,en,black,blaxploitation.n.01,definition,the exploitation of black people (especially with regard to stereotyped roles in movies),stereotyped,1 +pwn,en,homosexual,butch.s.02,definition,(of male or female homosexuals) characterized by stereotypically male traits or appearance,stereotypically,2 +pwn,en,madras,chennai.n.01,definition,a city in Tamil Nadu on the Bay of Bengal; formerly Madras,formerly,3 +pwn,en,descent,chink.n.01,definition,(ethnic slur) offensive term for a person of Chinese descent,slur,1 +pwn,en,descent,chink.n.01,definition,(ethnic slur) offensive term for a person of Chinese descent,offensive,1 +pwn,en,coolie,coolie.n.01,definition,(ethnic slur) an offensive name for an unskilled Asian laborer,slur,3 +pwn,en,coolie,coolie.n.01,definition,(ethnic slur) an offensive name for an unskilled Asian laborer,offensive,3 +pwn,en,eskimo,eskimo.n.01,definition,a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people'),call themselves,3 +pwn,en,inuit,eskimo.n.01,definition,a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people'),call themselves,3 +pwn,en,race,ethnic_slur.n.01,definition,a slur on someone's race or language,slur,1 +pwn,en,homosexual,fagot.n.01,definition,offensive term for a homosexual man,offensive,3 +pwn,en,queer,fagot.n.01,definition,offensive term for a homosexual man,offensive,3 +pwn,en,lilliputian,fiddling.s.01,definition,(informal) small and of little importance,informal,2 +pwn,en,gay,ghetto.n.02,definition,any segregated mode of living or working that results from bias or stereotyping,stereotyping,2 +pwn,en,descent,greaser.n.01,definition,(ethnic slur) offensive term for a person of Mexican descent,slur,1 +pwn,en,descent,greaser.n.01,definition,(ethnic slur) offensive term for a person of Mexican descent,offensive,1 +pwn,en,indian,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +pwn,en,caucasian,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +pwn,en,half-breed,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +pwn,en,descent,jap.n.01,definition,(offensive slang) offensive term for a person of Japanese descent,offensive,1 +pwn,en,kaffir,kaffir.n.02,definition,an offensive and insulting term for any Black African,offensive,3 +pwn,en,black,kaffir.n.02,definition,an offensive and insulting term for any Black African,offensive,3 +pwn,en,descent,kraut.n.01,definition,offensive term for a person of German descent,offensive,1 +pwn,en,native,levantine.n.01,definition,(formerly) a native or inhabitant of the Levant,formerly,1 +pwn,en,black,mammy.n.01,definition,an offensive term for a Black nursemaid in the southern U.S.,offensive,1 +pwn,en,mongoloid,mongoloid.a.03,definition,(offensive) of or relating to or suffering from Down syndrome,offensive,3 +pwn,en,mongoloid,mongoloid.n.02,definition,"a person suffering from Down syndrome (no longer used technically in this sense, now considered offensive)",offensive,3 +pwn,en,descent,paddy.n.01,definition,(ethnic slur) offensive term for a person of Irish descent,slur,1 +pwn,en,descent,paddy.n.01,definition,(ethnic slur) offensive term for a person of Irish descent,offensive,1 +pwn,en,black,pickaninny.n.01,definition,(ethnic slur) offensive term for a Black child,slur,1 +pwn,en,black,pickaninny.n.01,definition,(ethnic slur) offensive term for a Black child,offensive,1 +wikidata,en,white,Q1066801,description,pejorative,pejorative,1 +wikidata,en,servant,Q10705205,description,older term for domestic worker staying a long time for the same employer's family,older term,1 +wikidata,nl,blank,Q107405878,description,betreft de discussie of het gebruik van de term 'blank' racistisch is,racistisch,2 +wikidata,en,negro,Q1130557,description,historical word for black people,historical word,3 +wikidata,en,black,Q1130557,description,historical word for black people,historical word,3 +wikidata,nl,neger,Q1130557,description,historische term voor zwart persoon,historische term,3 +wikidata,nl,zwart,Q1130557,description,historische term voor zwart persoon,historische term,3 +wikidata,nl,ras,Q1130557,description,historische term voor zwart persoon,historische term,3 +wikidata,en,white,Q1135775,description,"derogatory term for poor, rural, usually white and male, person from the Southern United States",derogatory term,1 +wikidata,en,mongoloid,Q11410826,description,historical term used to refer to a sub-type of the Mongoloid race and classified by William W. Howells,historical term,2 +wikidata,en,negro,Q114217628,description,historical term in the Afroamerican emancipation,historical term,1 +wikidata,en,queer,Q115870510,description,identity term of a LGBT+ person,identity term,2 +wikidata,en,indian,Q12643403,description,obsolete name for a group of Ópata Indians,obsolete name,1 +wikidata,en,kaffir,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +wikidata,en,black,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +wikidata,en,indigenous,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +wikidata,nl,kaffer,Q1285250,description,"betekent ongelovige, ook wel voor sukkel of lomperik, en een scheldwoord",scheldwoord,3 +wikidata,en,barbarian,Q134313,description,person perceived to be either uncivilized or primitive based on stereotypes,stereotypes,3 +wikidata,en,primitive,Q134313,description,person perceived to be either uncivilized or primitive based on stereotypes,stereotypes,3 +wikidata,en,ethnic groups,Q1371427,description,derogatory term for an ethnic group,derogatory term,1 +wikidata,en,black,Q1455718,description,slur against black people,slur,1 +wikidata,en,homosexual,Q14634937,description,disparaging term used by opponents of gay rights activism,disparaging term,1 +wikidata,en,gay,Q14634937,description,disparaging term used by opponents of gay rights activism,disparaging term,1 +wikidata,en,immigrant,Q1532765,description,derogatory term mostly referring to Mexican illegal immigrants to the USA,derogatory term,1 +wikidata,en,aboriginal,Q16211163,description,term of self-reference for many Australian aboriginals,term of self-reference,1 +wikidata,en,hottentot,Q1631241,description,antiquated term for the Khoisan people of southern Africa.,antiquated,3 +wikidata,en,indigenous,Q16842904,description,informal term used in Australian English to refer to Indigenous Australians,informal term,1 +wikidata,en,native,Q17144151,description,obsolete term for mixed Native American and European ancestry,obsolete term,3 +wikidata,en,half-breed,Q17144151,description,obsolete term for mixed Native American and European ancestry,obsolete term,3 +wikidata,en,gay,Q1744361,description,gay slang term,slang term,1 +wikidata,en,retarded,Q18394147,description,pejorative slur for one with a mental disability,slur,3 +wikidata,en,retarded,Q18394147,description,pejorative slur for one with a mental disability,pejorative,3 +wikidata,nl,inuk,Q189975,description,naam waarmee de Eskimo's van Groenland en Canada zichzelf aanduiden,zichzelf aanduiden,3 +wikidata,nl,eskimo,Q189975,description,naam waarmee de Eskimo's van Groenland en Canada zichzelf aanduiden,zichzelf aanduiden,3 +wikidata,nl,homo,Q1975772,description,denigrerende term voor homo's,denigrerende,1 +wikidata,en,native,Q2023990,description,obsolete term for a physical type most common among populations native to the Iranian plateau,obsolete term,1 +wikidata,en,race,Q2090033,description,pejorative term referring to interethnic relationships resulting in multiethnic offspring,pejorative,1 +wikidata,en,black,Q2265295,description,genre of music that presented a stereotype of black people,stereotype,1 +wikidata,en,mohammedan,Q2367463,description,formerly common term referring to Islam,formerly common term,3 +wikidata,nl,lilliputter,Q2419953,description,informele term voor een mens met dwerggroei,informele term,3 +wikidata,nl,dwerg,Q2419953,description,informele term voor een mens met dwerggroei,informele term,3 +wikidata,en,gay,Q26791,description,a gay slang term for a woman who associates either mostly or exclusively with gay men,slang term,1 +wikidata,en,white,Q27556771,description,derogatory term,derogatory term,1 +wikidata,en,gay,Q2919166,description,gay slang term for a gay man,slang term,1 +wikidata,en,ethnicity,Q2920284,description,derogatory term for an Israeli man of Mizrahi ethnicity,derogatory term,1 +wikidata,nl,westers,Q30674738,description,denigrerend Chinees neologisme en politieke bijnaam voor westerse linkse ideologieën,denigrerend,1 +wikidata,en,gay,Q3624420,description,slang term for overweight gay man,slang term,1 +wikidata,en,berber,Q410453,description,"A historical term for all or most of sub-Saharan Africa or Black Africa, inclusive of much more than modern Ethiopia but almost never Egypt, Tunisia, or the land of the Berbers; in Greco-Roman mythology, considered devout and close to the gods",historical term,2 +wikidata,en,black,Q410453,description,"A historical term for all or most of sub-Saharan Africa or Black Africa, inclusive of much more than modern Ethiopia but almost never Egypt, Tunisia, or the land of the Berbers; in Greco-Roman mythology, considered devout and close to the gods",historical term,2 +wikidata,en,black,Q4117010,description,colloquial term derived from the ethnic slur against black people,slur,1 +wikidata,en,black,Q4117010,description,colloquial term derived from the ethnic slur against black people,colloquial term,1 +wikidata,en,aboriginal,Q442425,description,self identifying term used by number of Aboriginal groups in Austealia,self identifying term,1 +wikidata,en,white,Q45991,description,slang term for white person acting like a black person,slang term,1 +wikidata,en,black,Q45991,description,slang term for white person acting like a black person,slang term,1 +wikidata,en,slave,Q4666486,description,"Arabic pejorative meaning ""slave""",pejorative,1 +wikidata,en,mulatto,Q4689037,description,French pejorative term referring to a mulatto,pejorative,1 +wikidata,en,ethnicity,Q5101084,description,English-language ethnic slur usually referring to a person of Chinese or East Asian ethnicity,slur,1 +wikidata,en,indigenous,Q5140747,description,pejorative term referring to indigenous peoples of the United States and Canada,pejorative,1 +wikidata,en,ethnic groups,Q5158607,description,slang term for ethnic group,slang term,1 +wikidata,en,gay,Q5207989,description,slang term in gay culture meaning an older man sexually involved in a relationship or having a sexual interest in a younger man,slang term,2 +wikidata,en,gay,Q5528676,description,outdated medical term,outdated medical term,1 +wikidata,en,gay,Q55657493,description,"derogatory term ridiculing Europe's tolerance toward gay people, implying that all Europe is populated by gay people",derogatory term,1 +wikidata,nl,homo,Q55657493,description,"denigrerende term die de tolerantie van Europa ten opzichte van homo's belachelijk maakt, wat impliceert dat heel Europa door homo's wordt bevolkt",denigrerende,1 +wikidata,en,servant,Q56011985,description,"A humorous novel (though with some racial stereotyping) of a negro servant and his master, a planter.",stereotyping,1 +wikidata,en,negro,Q56011985,description,"A humorous novel (though with some racial stereotyping) of a negro servant and his master, a planter.",stereotyping,1 +wikidata,en,homosexual,Q5891541,description,archaic term for homosexual,archaic term,1 +wikidata,en,servant,Q5913718,description,derogatory term Afro-American who worked as a servant in post-slavery America,derogatory term,1 +wikidata,en,negro,Q5913718,description,derogatory term Afro-American who worked as a servant in post-slavery America,derogatory term,1 +wikidata,en,aboriginal,Q5940484,description,"slang term meaning ""begging"" in some Australian Aboriginal communities",slang term,1 +wikidata,en,ethnic groups,Q62928,description,obsolete term for an ethnic group in the Middle East,obsolete term,1 +wikidata,en,race,Q62928,description,obsolete term for an ethnic group in the Middle East,obsolete term,1 +wikidata,en,indian,Q6385618,description,derogatory term for ethnic Indians in Southeast Asia,derogatory term,1 +wikidata,en,white,Q6880109,description,pejorative expression previously used within the African-American community to refer to an imperious white man,pejorative,1 +wikidata,nl,blank,Q698752,description,racistische ideologie,racistische,2 +wikidata,en,white,Q7129609,description,outdated classification of humans,outdated classification,3 +wikidata,en,caucasian,Q7129609,description,outdated classification of humans,outdated classification,3 +wikidata,en,white,Q7549820,description,informal term for the white solid that results from the addition of soap to hard water,informal term,1 +wikidata,en,gypsy,Q76475,description,(denigrating) collective term for Roma and Yenish,denigrating,1 +wikidata,nl,zigeuner,Q76475,description,"als denigrerend beschouwde naam voor de Roma/Jenische, soms ook spreekwoordelijk gebruikt",denigrerend,3 +wikidata,en,homosexual,Q7831920,description,colloquial term for a casual homosexual partner,colloquial term,1 +wikidata,en,mulatto,Q7832650,description,stereotypical fictional character in 19th and 20th century American literature,stereotypical,2 +wikidata,en,gay,Q7845166,description,gay slang term for men who cruise for sex or potential sex partners or experiences,slang term,1 +wikidata,en,tribe,Q7855217,description,"historical term for ""military division, clan, or tribe"" among the Turkic peoples",historical term,1 +wikidata,en,immigrant,Q8072681,description,slang term used by Italian American mobsters to refer to newer immigrant Italian mobsters,slang term,1 +wikidata,en,black,Q817393,description,"a racialized classification of people, usually a political and skin color-based category for specific populations with a mid to dark brown complexion",racialized classification,3 +wikidata,en,gay,Q898608,description,"pejorative term for the alleged disproportional behind-the-scene influence of gay rights groups and the LGBT community in politics, media, culture, and everyday life",pejorative,1 +wikidata,en,descent,Q906267,description,"ethnic slur directed at people of Chinese descent, originated as the Japanese transliteration for word ""China""",slur,1 +wikidata,en,white,Q95530210,description,a common given name used as pejorative American slang term referring to a annoying white entitled woman,slang term,1 +wikidata,en,white,Q95530210,description,a common given name used as pejorative American slang term referring to a annoying white entitled woman,pejorative,1 +wikidata,en,homosexual,Q98113730,description,pejorative term for LGBT movements,pejorative,1 +pwn,en,discover,reconnaissance_in_force.n.01,definition,an offensive operation designed to discover or test the enemy's strength (or to obtain other information),offensive,1 +pwn,en,native,redskin.n.01,definition,(slang) offensive term for Native Americans,offensive,1 +pwn,en,white,sahib.n.01,definition,formerly a term of respect for important white Europeans in colonial India; used after the name,formerly,1 +pwn,en,descent,spic.n.01,definition,(ethnic slur) offensive term for persons of Latin American descent,slur,1 +pwn,en,descent,spic.n.01,definition,(ethnic slur) offensive term for persons of Latin American descent,offensive,1 +pwn,en,indian,squaw_man.n.01,definition,derogatory term for a white man married to a North American Indian woman,derogatory,1 +pwn,en,white,squaw_man.n.01,definition,derogatory term for a white man married to a North American Indian woman,derogatory,1 +pwn,en,indian,squaw.n.01,definition,derogatory terms for an American Indian woman,derogatory,1 +pwn,en,madras,tamil_nadu.n.01,definition,a state in southeastern India on the Bay of Bengal (south of Andhra Pradesh); formerly Madras,formerly,2 +pwn,en,gypsy,tinker.n.02,definition,formerly a person (traditionally a Gypsy) who traveled from place to place mending pots and kettles and other metal utensils as a way to earn a living,formerly,2 +pwn,en,white,white_trash.n.01,definition,(slang) an offensive term for White people who are impoverished,offensive,1 +pwn,en,white,whitey.n.01,definition,(slang) offensive names for a White man,offensive,1 +pwn,en,descent,wop.n.01,definition,(ethnic slur) offensive term for a person of Italian descent,slur,1 +pwn,en,descent,wop.n.01,definition,(ethnic slur) offensive term for a person of Italian descent,offensive,1 \ No newline at end of file diff --git a/sensitivity_markers/implicit/implicit_markers.json b/sensitivity_markers/implicit/implicit_markers.json index 985e5ac..d2c7604 100644 --- a/sensitivity_markers/implicit/implicit_markers.json +++ b/sensitivity_markers/implicit/implicit_markers.json @@ -43,7 +43,6 @@ "nl": ["negatieve bijklank", "(\\bgebruik\b).*(\\bspecifiek\\w*\\b)|(\\bspecifiek\\w*\\b).*(\\bgebruik\\b)", - "(\\bgebruik\\w*\\b).*(\\bterm\\w*\\b)|(\\bterm\\w*\\b).*(\\bgebruik\\w*\\b)", "verouderde benaming", "noemen zichzelf", "(\\bzichzelf\\b).*(\\b(aan)?duiden\\b)|(\\b(aan)?duiden\\b).*(\\bzichzelf\\b)"]}, diff --git a/sensitivity_markers/implicit/pwn_implicit.csv b/sensitivity_markers/implicit/pwn_implicit.csv new file mode 100644 index 0000000..30ebba1 --- /dev/null +++ b/sensitivity_markers/implicit/pwn_implicit.csv @@ -0,0 +1,104 @@ +,resource,lang,lemma,entity_id,property,value,implicit_marker,level +0,pwn,en,madras,tamil_nadu.n.01,definition,a state in southeastern India on the Bay of Bengal (south of Andhra Pradesh); formerly Madras,formerly,2 +1,pwn,en,madras,chennai.n.01,definition,a city in Tamil Nadu on the Bay of Bengal; formerly Madras,formerly,3 +2,pwn,en,immigrant,ellis_island.n.01,definition,an island in New York Bay that was formerly the principal immigration station for the United States,formerly,1 +3,pwn,en,indian,left-handed.s.02,definition,(of marriages) illicit or informal,informal,1 +4,pwn,en,indian,potlatch.n.01,definition,"a ceremonial feast held by some Indians of the northwestern coast of North America (as in celebrating a marriage or a new accession) in which the host gives gifts to tribesmen and others to display his superior wealth (sometimes, formerly, to his own impoverishment)",formerly,1 +5,pwn,en,indian,quechua.n.02,definition,a community of South American Indians in Peru who were formerly the ruling class of the Incan Empire,formerly,1 +6,pwn,en,indian,arapaho.n.01,definition,a member of a tribe of Plains Indians formerly inhabiting eastern Colorado and Wyoming (now living in Oklahoma and Wyoming),formerly,1 +7,pwn,en,indian,caddo.n.01,definition,a group of Plains Indians formerly living in what is now North and South Dakota and Nebraska and Kansas and Arkansas and Louisiana and Oklahoma and Texas,formerly,1 +8,pwn,en,indian,colorado_river_hemp.n.01,definition,tall-growing annual of southwestern United States widely grown as green manure; yields a strong tough bast fiber formerly used by Indians for cordage,formerly,1 +9,pwn,en,indian,atakapa.n.01,definition,a member of an Indian people formerly living along the Gulf Coast of Louisiana and Texas,formerly,1 +10,pwn,en,indian,chimariko.n.01,definition,a member of an extinct North American Indian people formerly living in California,formerly,1 +11,pwn,en,indian,iroquois.n.01,definition,any member of the warlike North American Indian peoples formerly living in New York State; the Iroquois League were allies of the British during the American Revolution,formerly,1 +12,pwn,en,indian,mohave.n.01,definition,a member of the North American Indian people formerly living in the Colorado river valley in Arizona and Nevada and California,formerly,1 +13,pwn,en,indian,quechua.n.01,definition,a member of a South American Indian people in Peru who were formerly the ruling class of the Inca empire,formerly,1 +14,pwn,en,indian,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +15,pwn,en,indian,squaw.n.01,definition,derogatory terms for an American Indian woman,derogatory,1 +16,pwn,en,indian,squaw_man.n.01,definition,derogatory term for a white man married to a North American Indian woman,derogatory,1 +17,pwn,en,indian,soma.n.01,definition,leafless East Indian vine; its sour milky juice formerly used to make an intoxicating drink,formerly,1 +18,pwn,en,homo,boskop_man.n.01,definition,possible early Homo sapiens represented by a cranium found in the Transvaal; formerly considered a separate species,formerly,1 +19,pwn,en,gypsy,tinker.n.02,definition,formerly a person (traditionally a Gypsy) who traveled from place to place mending pots and kettles and other metal utensils as a way to earn a living,formerly,2 +20,pwn,en,coolie,coolie.n.01,definition,(ethnic slur) an offensive name for an unskilled Asian laborer,slur,3 +21,pwn,en,coolie,coolie.n.01,definition,(ethnic slur) an offensive name for an unskilled Asian laborer,offensive,3 +22,pwn,en,white,fox_terrier.n.01,definition,small lively black-and-white terriers formerly used to dig out foxes,formerly,1 +23,pwn,en,white,bernese_mountain_dog.n.01,definition,large powerful long-haired black-coated Swiss dog with deep tan or russet markings on legs and white blaze and feet and chest marking; formerly used for draft,formerly,1 +24,pwn,en,white,theurgy.n.02,definition,white magic performed with the help of beneficent spirits (as formerly practiced by Neoplatonists),formerly,1 +25,pwn,en,white,white_trash.n.01,definition,(slang) an offensive term for White people who are impoverished,offensive,1 +26,pwn,en,white,whitey.n.01,definition,(slang) offensive names for a White man,offensive,1 +27,pwn,en,white,hunkpapa.n.01,definition,a member of the Siouan people who constituted a division of the Teton Sioux and who formerly lived in the western Dakotas; they were prominent in resisting the white encroachment into the northern Great Plains,formerly,1 +28,pwn,en,white,sahib.n.01,definition,formerly a term of respect for important white Europeans in colonial India; used after the name,formerly,1 +29,pwn,en,white,squaw_man.n.01,definition,derogatory term for a white man married to a North American Indian woman,derogatory,1 +30,pwn,en,white,dita.n.01,definition,evergreen tree of eastern Asia and Philippines having large leathery leaves and small green-white flowers in compact cymes; bark formerly used medicinally,formerly,1 +31,pwn,en,white,ivory_tree.n.01,definition,tropical Asian tree with hard white wood and bark formerly used as a remedy for dysentery and diarrhea,formerly,1 +32,pwn,en,white,boneset.n.02,definition,perennial herb of southeastern United States having white-rayed flower heads; formerly used as in folk medicine,formerly,1 +33,pwn,en,white,common_milkwort.n.01,definition,"small European perennial with numerous branches having racemes of blue, pink or white flowers; formerly reputed to promote human lactation",formerly,1 +34,pwn,en,white,whale_oil.n.01,definition,a white to brown oil obtained from whale blubber; formerly used as an illuminant,formerly,1 +35,pwn,en,caucasian,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +36,pwn,en,kaffir,kaffir.n.02,definition,an offensive and insulting term for any Black African,offensive,3 +37,pwn,en,descent,chink.n.01,definition,(ethnic slur) offensive term for a person of Chinese descent,slur,1 +38,pwn,en,descent,chink.n.01,definition,(ethnic slur) offensive term for a person of Chinese descent,offensive,1 +39,pwn,en,descent,paddy.n.01,definition,(ethnic slur) offensive term for a person of Irish descent,slur,1 +40,pwn,en,descent,paddy.n.01,definition,(ethnic slur) offensive term for a person of Irish descent,offensive,1 +41,pwn,en,descent,wop.n.01,definition,(ethnic slur) offensive term for a person of Italian descent,slur,1 +42,pwn,en,descent,wop.n.01,definition,(ethnic slur) offensive term for a person of Italian descent,offensive,1 +43,pwn,en,descent,jap.n.01,definition,(offensive slang) offensive term for a person of Japanese descent,offensive,1 +44,pwn,en,descent,spic.n.01,definition,(ethnic slur) offensive term for persons of Latin American descent,slur,1 +45,pwn,en,descent,spic.n.01,definition,(ethnic slur) offensive term for persons of Latin American descent,offensive,1 +46,pwn,en,descent,greaser.n.01,definition,(ethnic slur) offensive term for a person of Mexican descent,slur,1 +47,pwn,en,descent,greaser.n.01,definition,(ethnic slur) offensive term for a person of Mexican descent,offensive,1 +48,pwn,en,descent,kraut.n.01,definition,offensive term for a person of German descent,offensive,1 +49,pwn,en,mongoloid,mongoloid.n.02,definition,"a person suffering from Down syndrome (no longer used technically in this sense, now considered offensive)",offensive,3 +50,pwn,en,mongoloid,mongoloid.a.03,definition,(offensive) of or relating to or suffering from Down syndrome,offensive,3 +51,pwn,en,discover,reconnaissance_in_force.n.01,definition,an offensive operation designed to discover or test the enemy's strength (or to obtain other information),offensive,1 +52,pwn,en,homosexual,butch.s.02,definition,(of male or female homosexuals) characterized by stereotypically male traits or appearance,stereotypically,2 +53,pwn,en,homosexual,fagot.n.01,definition,offensive term for a homosexual man,offensive,3 +54,pwn,en,native,great_plains.n.01,definition,a vast prairie region extending from Alberta and Saskatchewan and Manitoba in Canada south through the west central United States into Texas; formerly inhabited by Native Americans,formerly,1 +55,pwn,en,native,redskin.n.01,definition,(slang) offensive term for Native Americans,offensive,1 +56,pwn,en,native,levantine.n.01,definition,(formerly) a native or inhabitant of the Levant,formerly,1 +57,pwn,en,native,giant_buttercup.n.01,definition,spectacular perennial native of wet montane grasslands of Peru; formerly included in genus Ranunculus,formerly,1 +58,pwn,en,native,catharanthus.n.01,definition,small genus of erect annual or perennial herbs native to Madagascar; widely naturalized in the tropics; formerly included in genus Vinca,formerly,1 +59,pwn,en,native,coltsfoot.n.02,definition,perennial herb with large rounded leaves resembling a colt's foot and yellow flowers appearing before the leaves do; native to Europe but now nearly cosmopolitan; used medicinally especially formerly,formerly,1 +60,pwn,en,native,common_thyme.n.01,definition,common aromatic garden perennial native to the western Mediterranean; used in seasonings and formerly as medicine,formerly,1 +61,pwn,en,negro,black.n.05,definition,"a person with African ancestry, and are archaic and pejorative today",pejorative,3 +62,pwn,en,roots,habenaria.n.01,definition,chiefly terrestrial orchids with tubers or fleshy roots often having long slender spurs and petals and lip lobes; includes species formerly placed in genus Gymnadeniopsis,formerly,1 +63,pwn,en,roots,madder.n.01,definition,Eurasian herb having small yellow flowers and red roots formerly an important source of the dye alizarin,formerly,1 +64,pwn,en,roots,sea_holly.n.01,definition,European evergreen eryngo with twisted spiny leaves naturalized on United States east coast; roots formerly used as an aphrodisiac,formerly,1 +65,pwn,en,roots,cynancum.n.01,definition,any of various mostly giant tropical lianas of Africa and Madagascar having greenish or purple flowers and long smooth pods; roots formerly used as an emetic,formerly,1 +66,pwn,en,western,benin.n.01,definition,a country on western coast of Africa; formerly under French control,formerly,1 +67,pwn,en,western,togo.n.01,definition,a republic on the western coast of Africa on the Gulf of Guinea; formerly under French control,formerly,1 +68,pwn,en,western,aachen.n.01,definition,a city in western Germany near the Dutch and Belgian borders; formerly it was Charlemagne's northern capital,formerly,1 +69,pwn,en,western,croatia.n.01,definition,a republic in the western Balkans in south-central Europe in the eastern Adriatic coastal area; formerly part of the Habsburg monarchy and Yugoslavia; became independent in 1991,formerly,1 +70,pwn,en,western,burkina_faso.n.01,definition,a desperately poor landlocked country in western Africa; was formerly Upper Volta under French rule but gained independence in 1960,formerly,1 +71,pwn,en,western,guinea.n.03,definition,a republic in western Africa on the Atlantic; formerly a French colony; achieved independence from France in 1958,formerly,1 +72,pwn,en,western,hejaz.n.01,definition,a coastal region of the western Arabian Peninsula bordering on the Red Sea; includes both Mecca and Medina; formerly an independent kingdom until it united with Nejd to form the Kingdom of Saudi Arabia,formerly,1 +73,pwn,en,western,klaipeda.n.01,definition,a city in western Lithuania on the Baltic Sea; formerly an important trading town of the Hanseatic League,formerly,1 +74,pwn,en,western,erie.n.01,definition,a member of an Iroquoian people formerly living on the south shore of Lake Erie in northern Ohio and northwest Pennsylvania and western New York,formerly,1 +75,pwn,en,western,hidatsa.n.01,definition,a member of the Sioux people formerly inhabiting an area along the Missouri river in western North Dakota,formerly,1 +76,pwn,en,western,hunkpapa.n.01,definition,a member of the Siouan people who constituted a division of the Teton Sioux and who formerly lived in the western Dakotas; they were prominent in resisting the white encroachment into the northern Great Plains,formerly,1 +77,pwn,en,western,oglala.n.01,definition,a member of the Siouan people who constituted a division of the Teton Sioux and who formerly inhabited the Black Hills of western South Dakota,formerly,1 +78,pwn,en,western,ingrian.n.01,definition,a member of western Finnish people formerly living in the Baltic province where Saint Petersburg was built,formerly,1 +79,pwn,en,western,calocedrus.n.01,definition,tall evergreens of western North America and eastern Asia; formerly included in genus Libocedrus,formerly,1 +80,pwn,en,western,gumweed.n.01,definition,any of various western American plants of the genus Grindelia having resinous leaves and stems formerly used medicinally; often poisonous to livestock,formerly,1 +81,pwn,en,western,common_thyme.n.01,definition,common aromatic garden perennial native to the western Mediterranean; used in seasonings and formerly as medicine,formerly,1 +82,pwn,en,eskimo,eskimo.n.01,definition,a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people'),call themselves,3 +83,pwn,en,gay,ghetto.n.02,definition,any segregated mode of living or working that results from bias or stereotyping,stereotyping,2 +84,pwn,en,inuit,eskimo.n.01,definition,a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people'),call themselves,3 +85,pwn,en,black,black.n.05,definition,"a person with African ancestry, and are archaic and pejorative today",pejorative,3 +86,pwn,en,black,blaxploitation.n.01,definition,the exploitation of black people (especially with regard to stereotyped roles in movies),stereotyped,1 +87,pwn,en,black,fox_terrier.n.01,definition,small lively black-and-white terriers formerly used to dig out foxes,formerly,1 +88,pwn,en,black,bernese_mountain_dog.n.01,definition,large powerful long-haired black-coated Swiss dog with deep tan or russet markings on legs and white blaze and feet and chest marking; formerly used for draft,formerly,1 +89,pwn,en,black,georgia.n.03,definition,a republic in Asia Minor on the Black Sea separated from Russia by the Caucasus mountains; formerly an Asian soviet but became independent in 1991,formerly,1 +90,pwn,en,black,oglala.n.01,definition,a member of the Siouan people who constituted a division of the Teton Sioux and who formerly inhabited the Black Hills of western South Dakota,formerly,1 +91,pwn,en,black,kaffir.n.02,definition,an offensive and insulting term for any Black African,offensive,3 +92,pwn,en,black,mammy.n.01,definition,an offensive term for a Black nursemaid in the southern U.S.,offensive,1 +93,pwn,en,black,pickaninny.n.01,definition,(ethnic slur) offensive term for a Black child,slur,1 +94,pwn,en,black,pickaninny.n.01,definition,(ethnic slur) offensive term for a Black child,offensive,1 +95,pwn,en,black,arrow_wood.n.02,definition,deciduous shrub of eastern North America having blue-black berries and tough pliant wood formerly used to make arrows,formerly,1 +96,pwn,en,queer,fagot.n.01,definition,offensive term for a homosexual man,offensive,3 +97,pwn,en,half-breed,half-breed.n.01,definition,an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry),offensive,3 +98,pwn,en,lilliputian,fiddling.s.01,definition,(informal) small and of little importance,informal,2 +99,pwn,en,race,ethnic_slur.n.01,definition,a slur on someone's race or language,slur,1 +100,pwn,en,primitive,monera.n.01,definition,prokaryotic bacteria and blue-green algae and various primitive pathogens; because of lack of consensus on how to divide the organisms into phyla informal names are used for the major divisions,informal,2 +101,pwn,en,primitive,homo_soloensis.n.01,definition,extinct primitive hominid of late Pleistocene; Java; formerly Javanthropus,formerly,1 +102,pwn,en,tribe,arapaho.n.01,definition,a member of a tribe of Plains Indians formerly inhabiting eastern Colorado and Wyoming (now living in Oklahoma and Wyoming),formerly,1 diff --git a/sensitivity_markers/implicit/searching_implicit_markers.ipynb b/sensitivity_markers/implicit/searching_implicit_markers.ipynb index bc23e77..7d3e711 100644 --- a/sensitivity_markers/implicit/searching_implicit_markers.ipynb +++ b/sensitivity_markers/implicit/searching_implicit_markers.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -15,7 +15,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -50,7 +50,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -60,7 +60,7 @@ " Returns pandas DataFrame\n", " '''\n", " \n", - " wd_implicit = pd.DataFrame(columns=[\"resource\",lang,\"lemma\",\"entity_id\",\"property\",\"value\",\"implicit_marker\",\"level\"])\n", + " wd_implicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"property\",\"value\",\"implicit_marker\",\"level\"])\n", " \n", " # importing implicit markers dict\n", " with open('/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/implicit_markers.json','r') as jf:\n", @@ -96,55 +96,63 @@ " level = \"2\"\n", " if hit[\"QID\"] in set(rm_quids):\n", " level = \"3\"\n", + " \n", + " for marker in implicit_markers[\"wikidata\"][lang]:\n", "\n", - " # check descriptions type\n", - " if type(hit[\"description\"]) == list:\n", - " for d in hit[\"description\"]:\n", - " # iterating over all markers\n", - " for marker in implicit_markers[\"wikidata\"][lang]:\n", + " # check descriptions type\n", + " if type(hit[\"description\"]) == list:\n", + " for d in hit[\"description\"]:\n", " match = re.search(f\"\\\\b{marker}\\\\b\",d)\n", " if match:\n", " row = [\"wikidata\",lang,lemma,hit[\"QID\"],\"description\",d,match[0],level]\n", " wd_implicit.loc[len(wd_implicit)] = row\n", "\n", - " if type(hit[\"description\"]) == str:\n", - " for marker in implicit_markers[\"wikidata\"][lang]:\n", + " if type(hit[\"description\"]) == str:\n", " match = re.search(f\"\\\\b{marker}\\\\b\",hit[\"description\"])\n", " if match:\n", " row = [\"wikidata\",lang,lemma,hit[\"QID\"],\"description\",hit[\"description\"],match[0],level]\n", " wd_implicit.loc[len(wd_implicit)] = row\n", " \n", - " return wd_implicit.drop_duplicates(ignore_index=True)" + " return wd_implicit.drop_duplicates([\"lemma\",\"entity_id\",\"value\",\"implicit_marker\"],ignore_index=True)" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - ":29: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", - " rm_quids = list(wd_rm[wd_rm[\"resource\"]==\"wikidata\"][wd_rm[\"lang\"]==lang][\"entity_id\"])\n" - ] - } - ], + "outputs": [], "source": [ "wd_nl_implicit = search_implicit_markers_wd(\"nl\")" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ - "# export csv\n", "wd_nl_implicit.to_csv(\"wd_nl_implicit.csv\")" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# if there are multiple markers in literal, group them\n", + "for group in wd_en_implicit.groupby([\"lemma\",\"entity_id\",\"value\"]):\n", + " if (len(group[1])) > 1:\n", + " grouped_markers = (list(group[1][\"implicit_marker\"]))\n", + " \n", + " row = [\"wikidata\",list(group[1][\"lang\"])[0],group[0][0],\\\n", + " group[0][1],list(group[1][\"property\"])[0],group[0][2],grouped_markers,\\\n", + " list(group[1][\"level\"])[0]]\n", + " \n", + " \n", + " print(row)" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -152,6 +160,264 @@ "## AAT" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "def search_implicit_markers_aat(lang:str):\n", + " '''\n", + " lang: str, \"en\" or \"nl\"\n", + " Returns pandas DataFrame\n", + " '''\n", + " \n", + " aat_implicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"property\",\"value\",\"implicit_marker\",\"level\"])\n", + " \n", + " # importing implicit markers dict\n", + " with open('/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/implicit_markers.json','r') as jf:\n", + " implicit_markers = json.load(jf)\n", + " \n", + " # importing all search results\n", + " with open(f\"/Users/anesterov/reps/LODlit/AAT/aat_query_results_{lang}.json\",'r') as jf:\n", + " aat_all = json.load(jf)\n", + " \n", + " # import subset\n", + " with open(f\"/Users/anesterov/reps/LODlit/AAT/aat_{lang}_subset.json\",'r') as jf:\n", + " aat_subset = json.load(jf)\n", + " \n", + " # get all QIDs in the subset\n", + " subset_uris = []\n", + " for hits in aat_subset.values():\n", + " for hit in hits:\n", + " subset_uris.append(hit[\"aat_uri\"])\n", + " \n", + " # import rm\n", + " aat_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + " rms = list(aat_rm[aat_rm[\"resource\"] == \"aat\"][aat_rm[\"lang\"] == lang][\"entity_id\"])\n", + " \n", + " for term, hits in aat_all.items():\n", + " lemma = get_lemma_by_term(term, lang)\n", + " \n", + " for hit in hits:\n", + "\n", + " level = \"1\"\n", + " # check entity level\n", + " if hit[\"aat_uri\"] in set(subset_uris):\n", + " level = \"2\"\n", + " if hit[\"aat_uri\"] in set(rms):\n", + " level = \"3\"\n", + " \n", + " for marker in implicit_markers[\"aat\"][lang]:\n", + " # searching in scopeNotes\n", + " match = re.search(f\"\\\\b{marker}\\\\b\",hit[\"scopeNote\"])\n", + " if match:\n", + " row = [\"aat\",lang,lemma,hit[\"aat_uri\"],\"scopeNote\",hit[\"scopeNote\"],match[0],level]\n", + " aat_implicit.loc[len(aat_implicit)] = row\n", + " \n", + " # searching in prefLabel comments\n", + " match = re.search(f\"\\\\b{marker}\\\\b\",hit[\"prefLabel_comment\"])\n", + " if match:\n", + " row = [\"aat\",lang,lemma,hit[\"aat_uri\"],\"prefLabel_comment\",hit[\"prefLabel_comment\"],match[0],level]\n", + " aat_implicit.loc[len(aat_implicit)] = row\n", + " \n", + " # searching in altLabel comments \n", + " for c in hit[\"altLabel_comment\"]:\n", + " match = re.search(f\"\\\\b{marker}\\\\b\",c)\n", + " if match:\n", + " row = [\"aat\",lang,lemma,hit[\"aat_uri\"],\"altLabel_comment\",c,match[0],level]\n", + " aat_implicit.loc[len(aat_implicit)] = row\n", + " \n", + " return aat_implicit.drop_duplicates([\"lemma\",\"entity_id\",\"property\",\"implicit_marker\"],ignore_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_nl_implicit = search_implicit_markers_aat(\"nl\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export csv\n", + "aat_nl_implicit.to_csv(\"aat_nl_implicit.csv\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## PWN" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "pwn_implicit = pd.DataFrame(columns=[\"resource\",\"lang\",\"lemma\",\"entity_id\",\"property\",\"value\",\"implicit_marker\",\"level\"])\n", + " \n", + "# importing implicit markers dict\n", + "with open('/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/implicit_markers.json','r') as jf:\n", + " implicit_markers = json.load(jf)\n", + "\n", + "# importing all search results\n", + "with open(f\"/Users/anesterov/reps/LODlit/PWN/pwn31_query_results.json\",'r') as jf:\n", + " pwn_all = json.load(jf)\n", + "\n", + "# import subset\n", + "with open(f\"/Users/anesterov/reps/LODlit/PWN/pwn_subset.json\",'r') as jf:\n", + " pwn_subset = json.load(jf)\n", + "\n", + "# get all QIDs in the subset\n", + "subset = []\n", + "for hits in pwn_subset.values():\n", + " for hit in hits:\n", + " subset.append(hit[\"synset_id\"])\n", + "\n", + "# import rm\n", + "pwn_rm = pd.read_csv(\"/Users/anesterov/reps/LODlit/rm/rm_entities_unique.csv\")\n", + "rms = list(pwn_rm[pwn_rm[\"resource\"] == \"pwn\"][\"entity_id\"])\n", + "\n", + "for term, hits in pwn_all.items():\n", + " lemma = get_lemma_by_term(term, \"en\")\n", + " \n", + " for hit in hits:\n", + "\n", + " level = \"1\"\n", + " # check entity level\n", + " if hit[\"synset_id\"] in set(subset):\n", + " level = \"2\"\n", + " if hit[\"synset_id\"] in set(rms):\n", + " level = \"3\"\n", + " \n", + " for marker in implicit_markers[\"pwn\"][\"en\"]:\n", + " # searching in definitions\n", + " match = re.search(f\"\\\\b{marker}\\\\b\",hit[\"definition\"])\n", + " if match:\n", + " row = [\"pwn\",\"en\",lemma,hit[\"synset_id\"],\"definition\",hit[\"definition\"],match[0],level]\n", + " pwn_implicit.loc[len(pwn_implicit)] = row" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export csv\n", + "pwn_implicit.drop_duplicates([\"lemma\",\"entity_id\",\"value\",\"implicit_marker\"],ignore_index=True).to_csv(\"pwn_implicit.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# There are no implicit markers in ODWN" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "### merge wikidata" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "wd_en_impl = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/wd_en_implicit.csv\")\n", + "wd_nl_impl = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/wd_nl_implicit.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "frames = [wd_en_impl,wd_nl_impl]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "wd_impl = pd.concat(frames,ignore_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "wd_impl.to_csv(\"wd_implicit.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "### merge aat" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_en_impl = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/aat_en_implicit.csv\")\n", + "aat_nl_impl = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/aat_nl_implicit.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "frames = [aat_en_impl,aat_nl_impl]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_impl = pd.concat(frames,ignore_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "aat_impl.to_csv(\"aat_implicit.csv\")" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/sensitivity_markers/implicit/wd_en_implicit.csv b/sensitivity_markers/implicit/wd_en_implicit.csv index c9ddce3..0b3f07a 100644 --- a/sensitivity_markers/implicit/wd_en_implicit.csv +++ b/sensitivity_markers/implicit/wd_en_implicit.csv @@ -1,4 +1,4 @@ -,resource,en,lemma,entity_id,property,value,implicit_marker,level +,resource,lang,lemma,entity_id,property,value,implicit_marker,level 0,wikidata,en,immigrant,Q1532765,description,derogatory term mostly referring to Mexican illegal immigrants to the USA,derogatory term,1 1,wikidata,en,immigrant,Q8072681,description,slang term used by Italian American mobsters to refer to newer immigrant Italian mobsters,slang term,1 2,wikidata,en,barbarian,Q134313,description,person perceived to be either uncivilized or primitive based on stereotypes,stereotypes,3 diff --git a/sensitivity_markers/implicit/wd_implicit.csv b/sensitivity_markers/implicit/wd_implicit.csv new file mode 100644 index 0000000..9cbbfd4 --- /dev/null +++ b/sensitivity_markers/implicit/wd_implicit.csv @@ -0,0 +1,91 @@ +,Unnamed: 0,resource,lang,lemma,entity_id,property,value,implicit_marker,level +0,0,wikidata,en,immigrant,Q1532765,description,derogatory term mostly referring to Mexican illegal immigrants to the USA,derogatory term,1 +1,1,wikidata,en,immigrant,Q8072681,description,slang term used by Italian American mobsters to refer to newer immigrant Italian mobsters,slang term,1 +2,2,wikidata,en,barbarian,Q134313,description,person perceived to be either uncivilized or primitive based on stereotypes,stereotypes,3 +3,3,wikidata,en,indian,Q6385618,description,derogatory term for ethnic Indians in Southeast Asia,derogatory term,1 +4,4,wikidata,en,indian,Q12643403,description,obsolete name for a group of Ópata Indians,obsolete name,1 +5,5,wikidata,en,servant,Q5913718,description,derogatory term Afro-American who worked as a servant in post-slavery America,derogatory term,1 +6,6,wikidata,en,servant,Q10705205,description,older term for domestic worker staying a long time for the same employer's family,older term,1 +7,7,wikidata,en,servant,Q56011985,description,"A humorous novel (though with some racial stereotyping) of a negro servant and his master, a planter.",stereotyping,1 +8,8,wikidata,en,hottentot,Q1631241,description,antiquated term for the Khoisan people of southern Africa.,antiquated,3 +9,9,wikidata,en,gypsy,Q76475,description,(denigrating) collective term for Roma and Yenish,denigrating,1 +10,10,wikidata,en,white,Q7129609,description,outdated classification of humans,outdated classification,3 +11,11,wikidata,en,white,Q1066801,description,pejorative,pejorative,1 +12,12,wikidata,en,white,Q95530210,description,a common given name used as pejorative American slang term referring to a annoying white entitled woman,slang term,1 +13,13,wikidata,en,white,Q95530210,description,a common given name used as pejorative American slang term referring to a annoying white entitled woman,pejorative,1 +14,14,wikidata,en,white,Q1135775,description,"derogatory term for poor, rural, usually white and male, person from the Southern United States",derogatory term,1 +15,15,wikidata,en,white,Q27556771,description,derogatory term,derogatory term,1 +16,16,wikidata,en,white,Q7549820,description,informal term for the white solid that results from the addition of soap to hard water,informal term,1 +17,17,wikidata,en,white,Q45991,description,slang term for white person acting like a black person,slang term,1 +18,18,wikidata,en,white,Q6880109,description,pejorative expression previously used within the African-American community to refer to an imperious white man,pejorative,1 +19,19,wikidata,en,caucasian,Q7129609,description,outdated classification of humans,outdated classification,3 +20,20,wikidata,en,kaffir,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +21,21,wikidata,en,descent,Q906267,description,"ethnic slur directed at people of Chinese descent, originated as the Japanese transliteration for word ""China""",slur,1 +22,22,wikidata,en,mohammedan,Q2367463,description,formerly common term referring to Islam,formerly common term,3 +23,23,wikidata,en,mongoloid,Q11410826,description,historical term used to refer to a sub-type of the Mongoloid race and classified by William W. Howells,historical term,2 +24,24,wikidata,en,homosexual,Q14634937,description,disparaging term used by opponents of gay rights activism,disparaging term,1 +25,25,wikidata,en,homosexual,Q5891541,description,archaic term for homosexual,archaic term,1 +26,26,wikidata,en,homosexual,Q7831920,description,colloquial term for a casual homosexual partner,colloquial term,1 +27,27,wikidata,en,homosexual,Q98113730,description,pejorative term for LGBT movements,pejorative,1 +28,28,wikidata,en,native,Q2023990,description,obsolete term for a physical type most common among populations native to the Iranian plateau,obsolete term,1 +29,29,wikidata,en,native,Q17144151,description,obsolete term for mixed Native American and European ancestry,obsolete term,3 +30,30,wikidata,en,negro,Q1130557,description,historical word for black people,historical word,3 +31,31,wikidata,en,negro,Q114217628,description,historical term in the Afroamerican emancipation,historical term,1 +32,32,wikidata,en,negro,Q5913718,description,derogatory term Afro-American who worked as a servant in post-slavery America,derogatory term,1 +33,33,wikidata,en,negro,Q56011985,description,"A humorous novel (though with some racial stereotyping) of a negro servant and his master, a planter.",stereotyping,1 +34,34,wikidata,en,berber,Q410453,description,"A historical term for all or most of sub-Saharan Africa or Black Africa, inclusive of much more than modern Ethiopia but almost never Egypt, Tunisia, or the land of the Berbers; in Greco-Roman mythology, considered devout and close to the gods",historical term,2 +35,35,wikidata,en,mulatto,Q4689037,description,French pejorative term referring to a mulatto,pejorative,1 +36,36,wikidata,en,mulatto,Q7832650,description,stereotypical fictional character in 19th and 20th century American literature,stereotypical,2 +37,37,wikidata,en,aboriginal,Q16211163,description,term of self-reference for many Australian aboriginals,term of self-reference,1 +38,38,wikidata,en,aboriginal,Q442425,description,self identifying term used by number of Aboriginal groups in Austealia,self identifying term,1 +39,39,wikidata,en,aboriginal,Q5940484,description,"slang term meaning ""begging"" in some Australian Aboriginal communities",slang term,1 +40,40,wikidata,en,gay,Q14634937,description,disparaging term used by opponents of gay rights activism,disparaging term,1 +41,41,wikidata,en,gay,Q5528676,description,outdated medical term,outdated medical term,1 +42,42,wikidata,en,gay,Q898608,description,"pejorative term for the alleged disproportional behind-the-scene influence of gay rights groups and the LGBT community in politics, media, culture, and everyday life",pejorative,1 +43,43,wikidata,en,gay,Q26791,description,a gay slang term for a woman who associates either mostly or exclusively with gay men,slang term,1 +44,44,wikidata,en,gay,Q3624420,description,slang term for overweight gay man,slang term,1 +45,45,wikidata,en,gay,Q5207989,description,slang term in gay culture meaning an older man sexually involved in a relationship or having a sexual interest in a younger man,slang term,2 +46,46,wikidata,en,gay,Q7845166,description,gay slang term for men who cruise for sex or potential sex partners or experiences,slang term,1 +47,47,wikidata,en,gay,Q2919166,description,gay slang term for a gay man,slang term,1 +48,48,wikidata,en,gay,Q1744361,description,gay slang term,slang term,1 +49,49,wikidata,en,gay,Q55657493,description,"derogatory term ridiculing Europe's tolerance toward gay people, implying that all Europe is populated by gay people",derogatory term,1 +50,50,wikidata,en,black,Q817393,description,"a racialized classification of people, usually a political and skin color-based category for specific populations with a mid to dark brown complexion",racialized classification,3 +51,51,wikidata,en,black,Q1130557,description,historical word for black people,historical word,3 +52,52,wikidata,en,black,Q1455718,description,slur against black people,slur,1 +53,53,wikidata,en,black,Q410453,description,"A historical term for all or most of sub-Saharan Africa or Black Africa, inclusive of much more than modern Ethiopia but almost never Egypt, Tunisia, or the land of the Berbers; in Greco-Roman mythology, considered devout and close to the gods",historical term,2 +54,54,wikidata,en,black,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +55,55,wikidata,en,black,Q4117010,description,colloquial term derived from the ethnic slur against black people,slur,1 +56,56,wikidata,en,black,Q4117010,description,colloquial term derived from the ethnic slur against black people,colloquial term,1 +57,57,wikidata,en,black,Q2265295,description,genre of music that presented a stereotype of black people,stereotype,1 +58,58,wikidata,en,black,Q45991,description,slang term for white person acting like a black person,slang term,1 +59,59,wikidata,en,queer,Q115870510,description,identity term of a LGBT+ person,identity term,2 +60,60,wikidata,en,ethnic groups,Q1371427,description,derogatory term for an ethnic group,derogatory term,1 +61,61,wikidata,en,ethnic groups,Q62928,description,obsolete term for an ethnic group in the Middle East,obsolete term,1 +62,62,wikidata,en,ethnic groups,Q5158607,description,slang term for ethnic group,slang term,1 +63,63,wikidata,en,half-breed,Q17144151,description,obsolete term for mixed Native American and European ancestry,obsolete term,3 +64,64,wikidata,en,race,Q62928,description,obsolete term for an ethnic group in the Middle East,obsolete term,1 +65,65,wikidata,en,race,Q2090033,description,pejorative term referring to interethnic relationships resulting in multiethnic offspring,pejorative,1 +66,66,wikidata,en,primitive,Q134313,description,person perceived to be either uncivilized or primitive based on stereotypes,stereotypes,3 +67,67,wikidata,en,retarded,Q18394147,description,pejorative slur for one with a mental disability,slur,3 +68,68,wikidata,en,retarded,Q18394147,description,pejorative slur for one with a mental disability,pejorative,3 +69,69,wikidata,en,slave,Q4666486,description,"Arabic pejorative meaning ""slave""",pejorative,1 +70,70,wikidata,en,ethnicity,Q2920284,description,derogatory term for an Israeli man of Mizrahi ethnicity,derogatory term,1 +71,71,wikidata,en,ethnicity,Q5101084,description,English-language ethnic slur usually referring to a person of Chinese or East Asian ethnicity,slur,1 +72,72,wikidata,en,indigenous,Q1285250,description,"a slur used to refer to indigenous black people in South Africa; derived from the Arabic term for ""unbeliever"", i.e. pagan",slur,3 +73,73,wikidata,en,indigenous,Q5140747,description,pejorative term referring to indigenous peoples of the United States and Canada,pejorative,1 +74,74,wikidata,en,indigenous,Q16842904,description,informal term used in Australian English to refer to Indigenous Australians,informal term,1 +75,75,wikidata,en,tribe,Q7855217,description,"historical term for ""military division, clan, or tribe"" among the Turkic peoples",historical term,1 +76,0,wikidata,nl,lilliputter,Q2419953,description,informele term voor een mens met dwerggroei,informele term,3 +77,1,wikidata,nl,homo,Q1975772,description,denigrerende term voor homo's,denigrerende,1 +78,2,wikidata,nl,homo,Q55657493,description,"denigrerende term die de tolerantie van Europa ten opzichte van homo's belachelijk maakt, wat impliceert dat heel Europa door homo's wordt bevolkt",denigrerende,1 +79,3,wikidata,nl,westers,Q30674738,description,denigrerend Chinees neologisme en politieke bijnaam voor westerse linkse ideologieën,denigrerend,1 +80,4,wikidata,nl,neger,Q1130557,description,historische term voor zwart persoon,historische term,3 +81,5,wikidata,nl,inuk,Q189975,description,naam waarmee de Eskimo's van Groenland en Canada zichzelf aanduiden,zichzelf aanduiden,3 +82,6,wikidata,nl,blank,Q698752,description,racistische ideologie,racistische,2 +83,7,wikidata,nl,blank,Q107405878,description,betreft de discussie of het gebruik van de term 'blank' racistisch is,racistisch,2 +84,8,wikidata,nl,zigeuner,Q76475,description,"als denigrerend beschouwde naam voor de Roma/Jenische, soms ook spreekwoordelijk gebruikt",denigrerend,3 +85,9,wikidata,nl,zwart,Q1130557,description,historische term voor zwart persoon,historische term,3 +86,10,wikidata,nl,dwerg,Q2419953,description,informele term voor een mens met dwerggroei,informele term,3 +87,11,wikidata,nl,ras,Q1130557,description,historische term voor zwart persoon,historische term,3 +88,12,wikidata,nl,eskimo,Q189975,description,naam waarmee de Eskimo's van Groenland en Canada zichzelf aanduiden,zichzelf aanduiden,3 +89,13,wikidata,nl,kaffer,Q1285250,description,"betekent ongelovige, ook wel voor sukkel of lomperik, en een scheldwoord",scheldwoord,3 diff --git a/sensitivity_markers/implicit/wd_nl_implicit.csv b/sensitivity_markers/implicit/wd_nl_implicit.csv index 9b13cf2..84a686c 100644 --- a/sensitivity_markers/implicit/wd_nl_implicit.csv +++ b/sensitivity_markers/implicit/wd_nl_implicit.csv @@ -1,4 +1,4 @@ -,resource,nl,lemma,entity_id,property,value,implicit_marker,level +,resource,lang,lemma,entity_id,property,value,implicit_marker,level 0,wikidata,nl,lilliputter,Q2419953,description,informele term voor een mens met dwerggroei,informele term,3 1,wikidata,nl,homo,Q1975772,description,denigrerende term voor homo's,denigrerende,1 2,wikidata,nl,homo,Q55657493,description,"denigrerende term die de tolerantie van Europa ten opzichte van homo's belachelijk maakt, wat impliceert dat heel Europa door homo's wordt bevolkt",denigrerende,1 diff --git a/sensitivity_markers/selected_cases.ipynb b/sensitivity_markers/selected_cases.ipynb new file mode 100644 index 0000000..4f4a17a --- /dev/null +++ b/sensitivity_markers/selected_cases.ipynb @@ -0,0 +1,3270 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import pandas as pd\n", + "import csv" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# import implicit markers\n", + "implicit_markers = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/implicit/implicit_all.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "# import explicit markers\n", + "explicit_markers = pd.read_csv(\"/Users/anesterov/reps/LODlit/sensitivity_markers/explicit/explicit_all.csv\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Wikidata" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "lang = \"nl\"" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [], + "source": [ + "# import subset\n", + "with open(f\"/Users/anesterov/reps/LODlit/Wikidata/wd_{lang}_subset.json\",'r') as jf:\n", + " wd_subset = json.load(jf)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + ":2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", + " e_wd_implicit = implicit_markers[implicit_markers[\"resource\"] == \"wikidata\"][implicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n", + ":4: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", + " e_wd_explicit = explicit_markers[explicit_markers[\"resource\"] == \"wikidata\"][explicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n" + ] + } + ], + "source": [ + "# WD EN entities with implicit markers\n", + "e_wd_implicit = implicit_markers[implicit_markers[\"resource\"] == \"wikidata\"][implicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n", + "# WD EN entities with explicit markers\n", + "e_wd_explicit = explicit_markers[explicit_markers[\"resource\"] == \"wikidata\"][explicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 1" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal Q2479183 Canadian aboriginal syllabics\n", + "aboriginal Q100341850 Aboriginal kunst\n", + "aboriginal Q5375657 Encyclopaedia of Aboriginal Australia\n", + "aboriginals Q110629929 Etnologische tentoonstelling met Australische Aboriginals\n", + "achterlijk Q10388983 achterlijk (zeil)\n", + "afkomst Q55350216 afkomst, herinnering & plek\n", + "afkomst Q9031543 Categorie:Heilige of zalige van koninklijke afkomst\n", + "allochtone Q2098138 allochtone ouderen\n", + "allochtone Q55829603 Steunpunt Allochtone Meisjes & Vrouwen - Samv\n", + "allochtonen Q111256319 Haagse Allochtonen Partij\n", + "allochtoon Q1979583 Allochtoon\n", + "allochtoon Q2008347 allochtoon\n", + "baboe Q28090055 Studie (Baboe)\n", + "baboe Q43088035 Studie (Baboe)\n", + "barbaar Q189169 Conan de Barbaar\n", + "barbaar Q2469867 Cohen de Barbaar\n", + "barbaar Q2498891 De barbaar\n", + "barbaren Q57506011 De Barbaren (2015-2016)\n", + "barbaren Q57513626 De Barbaren (2014-2015)\n", + "batavia Q106686922 Wapen van Batavia\n", + "batavia Q1199713 Batavia\n", + "batavia Q2436746 VV Batavia\n", + "batavia Q4868680 Batavia Veterans Administration Hospital\n", + "batavia Q84322891 Multifilm Batavia\n", + "batavia Q2117912 SV Batavia '90\n", + "bedienden Q45021418 Ziekenfonds Landelijke Bedienden Centrale en Vooruitzicht Buurtspoorwegen\n", + "bedienden Q57076065 Algemeen Syndicaat van Reizigers, Bedienden, Handelaars en Patroons\n", + "bedienden Q71171864 Categorie:Bond van Bedienden, Technici en Kaderleden-bestuurder\n", + "berber Q21143451 Berber\n", + "berber Q2152757 Berber Jews\n", + "berber Q375935 Berber, Sudan\n", + "berber Q3807949 Jerba Berber\n", + "berber Q818743 Berber Academie\n", + "berbers Q100340157 Berbers in Marokko\n", + "berbers Q2712462 Berbers geloof\n", + "berbers Q33061123 Categorie:Zelfstandig naamwoord in het Berbers\n", + "berbers Q45315 Berbers\n", + "berbers Q55355256 Magisch Marokko, landelijke culturen in Marokko, de Berbers\n", + "birma Q2376315 Brits-Birma\n", + "birma Q2563642 Birma op de Olympische Zomerspelen 1956\n", + "birma Q2664805 Birma op de Olympische Zomerspelen 1984\n", + "birma Q2664807 Birma op de Olympische Zomerspelen 1980\n", + "birma Q2666064 Birma op de Olympische Zomerspelen 1960\n", + "birma Q2666080 Birma op de Olympische Zomerspelen 1988\n", + "birma Q2667140 Birma op de Olympische Zomerspelen 1964\n", + "birma Q704358 Staat Birma\n", + "birma Q776524 Birma op de Olympische Zomerspelen 1952\n", + "blank Q2560112 blank seperatisme\n", + "blanke Q49078 blanke Amerikanen\n", + "blanke Q59786221 Blanke Helle\n", + "blanken Q22909760 complottheorie voor genocide van blanken\n", + "blanken Q235155 blanken\n", + "bombay Q2550212 De Bombay\n", + "calcutta Q1348 Calcutta\n", + "calcutta Q5018950 Calcutta Riverside\n", + "derde wereld Q100340135 Traditionele vroedvrouwen in de Derde Wereld\n", + "derde wereld Q100341393 Traditionele vroedvrouwen uit de derde wereld\n", + "derde wereld Q180194 derde wereld\n", + "derde wereld Q20656136 Het Theater van de Derde Wereld in Europa\n", + "derde wereld Q85318651 De Derde Wereld als verdichtsel\n", + "dwerg Q10477881 dwerg in een fictiewerk\n", + "dwerg Q136562 Pulserende witte dwerg\n", + "dwerg Q17480821 fictieve bruine dwerg\n", + "dwerg Q56299838 Dwerg met zwaard, in aanvallende houding\n", + "dwerg Q5871 witte dwerg\n", + "dwerg Q5976 Zwarte dwerg\n", + "dwergen Q3478903 Zeven ringen van de dwergen\n", + "dwergen Q56508630 Verschillende misvormde dwergen\n", + "eerste wereld Q876830 eerste wereld\n", + "eskimo Q100342131 Tiderida, van Eskimo tot Groenlander\n", + "eskimo Q19365020 Eskimo Hill\n", + "eskimo Q20736 Eskimo\n", + "eskimo Q51512437 Nunivak Island Eskimo\n", + "eskimo Q8421920 Categorie:Eskimo-Aleoetische taalfamilie\n", + "eskimo's Q131242 eskimo's\n", + "eskimo's Q2659059 Paleo-Eskimo's\n", + "eskimo's Q3347113 Neo-Eskimo's\n", + "etniciteit Q5404323 etniciteit\n", + "etniciteit Q7128854 Categorie:Persoon naar etniciteit\n", + "etnische groep Q41710 etnische groep\n", + "etnische groep Q4204501 historische etnische groep\n", + "etnische groepen Q105999586 Wikidata-eigenschap gerelateerd aan etnische groepen of inheemse volkeren\n", + "gay Q1496534 Gay\n", + "gay Q592 gay\n", + "gay Q1383254 Ex-ex-gay\n", + "gay Q111748392 Gay\n", + "gay Q3723183 Elisabeth Gay\n", + "gay Q55186653 Mister Gay Netherlands\n", + "gehandicapte Q15978181 gehandicapte\n", + "gehandicapten Q18089065 Partij Voor Gehandicapten en Welzijn\n", + "gehandicapten Q2380034 Wet voorzieningen gehandicapten\n", + "gehandicapten Q2523708 Wet tegemoetkoming chronisch zieken en gehandicapten\n", + "gehandicapten Q29584864 Maatschappelijke dienstverlening zonder huisvesting voor ouderen en lichamelijk gehandicapten\n", + "gehandicapten Q47189385 Vormingsinstituut voor Begeleiding van Gehandicapten\n", + "gehandicapten Q61857538 activist voor rechten van gehandicapten\n", + "gekleurd Q1836236 Kleur op doek. Hoe exotische weefsels worden gekleurd\n", + "gekleurde Q2072081 gekleurde\n", + "gekleurde Q22245963 Vrouw met gekleurde hond\n", + "gekleurde Q4854529 gekleurde ruis\n", + "gekleurde Q61944902 Moeder Gods Kazanskaja, met koperen oklad en textiel met gekleurde glasstenen\n", + "gekleurde Q8230758 gekleurde contactlens\n", + "halfbloed Q18336298 De halfbloed\n", + "handicap Q1179623 lichamelijke handicap\n", + "handicap Q12131 handicap\n", + "handicap Q1818174 Wet gelijke behandeling op grond van handicap of chronische ziekte\n", + "handicap Q29584860 Instellingen met huisvesting voor personen met een mentale handicap of psychiatrische problemen en voor drugs- en alcoholverslaafden\n", + "handicap Q29584861 Instellingen met huisvesting voor ouderen en voor personen met een lichamelijke handicap\n", + "handicap Q42255152 Wikidata-eigenschap gerelateerd aan handicap\n", + "hermafrodiet Q22257088 Werkkledij van de belgische hermafrodiet, maar niet te fanatiek\n", + "hermafrodiet Q28097260 Hermafrodiet\n", + "hermafrodiet Q303479 hermafrodiet\n", + "homo Q105784 Homo heidelbergensis\n", + "homo Q3786468 Homo magi\n", + "homo Q40221 Homo-icoon\n", + "homoseksualiteit Q1348938 homoseksualiteit in India\n", + "homoseksualiteit Q1626313 homoseksualiteit in Japan\n", + "homoseksualiteit Q18349938 homoseksualiteit in Mexico\n", + "homoseksualiteit Q27333507 homoseksualiteit in Koerdistan\n", + "homoseksualiteit Q3882309 Homoseksualiteit in de middeleeuwen\n", + "homoseksualiteit Q6457893 homoseksualiteit in Nederland\n", + "homoseksualiteit Q6636 homoseksualiteit\n", + "homoseksualiteit Q8035007 Categorie:Mannelijke homoseksualiteit\n", + "homoseksualiteit Q8225766 homoseksualiteit in de samenleving\n", + "homoseksueel Q113286753 Homoseksueel\n", + "homoseksuele Q104969456 homoseksuele man\n", + "homoseksuele Q17015701 homoseksuele handelingen\n", + "homoseksuele Q2249431 homoseksuele prostitutie\n", + "indianen Q100340285 Indianen van Latijns Amerika\n", + "indianen Q100341399 Indianen Verhalen\n", + "indianen Q16910544 geschiedenis van de Indianen in de Verenigde Staten\n", + "indianen Q47534052 De keizerlijke troepen brengen de Indianen beschaving\n", + "indianen Q6979964 Controverse over het benoemen van de Indianen\n", + "indische Q605901 Zweedse Oost-Indische Compagnie\n", + "indische Q652560 West-Indische Federatie\n", + "indische Q1270312 Deense West-Indische en Guineese Compagnie\n", + "indische Q100341198 Nederlandsche West-Indische Tentoonstelling\n", + "indische Q826616 Deense Oost-Indische Compagnie\n", + "indo Q215643 Indo-Grieken\n", + "indo Q240123 Indo-Scythen\n", + "indo Q475027 Indo-Europeanen\n", + "indo Q269145 Indo-Arische migratie-theorie\n", + "indo Q60741209 Indo-Māori\n", + "indo Q61896194 De vergeten krijgers : de onvoorwaardelijke trouw van de Indo-Afrikaanse gemeenschap aan de Nederlandse vlag\n", + "inheemse Q103817 inheemse bevolking\n", + "inheemse Q1363781 inheemse volkeren in Brazilië\n", + "inheemse Q1493806 inheemse bevolking van Australië\n", + "inheemse Q216839 Inheemse volken van Taiwan\n", + "inheemse Q3987120 inheemse volken van de Arctische regio\n", + "inlander Q1945590 Inlander\n", + "inlanders Q100341039 Beeldgroepen van Inlanders uit den Indischen archipel\n", + "inlanders Q112845940 Gevecht tussen Nederlandse militairen en inlanders\n", + "inuit Q100341703 Canadese Inuit Kunst\n", + "inuit Q1091412 Inuit Tapiriit Kanatami\n", + "inuit Q1128374 Inuit Ataqatigiit\n", + "inuit Q22444905 Inuit Islet\n", + "inuit Q887850 Groenlandse Inuit\n", + "inuk Q47465549 Inuk\n", + "jap Q173712 JAP\n", + "jap Q2294900 Harding-JAP\n", + "jap Q2369794 King-JAP\n", + "jap Q3133637 Invincible-JAP\n", + "jap Q3156859 JAP\n", + "jap Q54898510 JAP-NF\n", + "jap Q58150158 1 Jap. Sicheltanne\n", + "jappenkamp Q70320605 Jappenkamp in Makassar\n", + "jappenkamp Q9073603 Categorie:Persoon in een Jappenkamp\n", + "kaukasische Q169921 Kaukasische talen\n", + "kaukasische Q2528872 Kaukasische wisent\n", + "kaukasische Q38576 Kaukasische owcharka\n", + "kaukasische Q55354560 Kaukasische volkeren\n", + "kaukasische Q5602078 Kaukasische Grieken\n", + "knecht Q108839781 Collectie Knecht-Drenth\n", + "knecht Q113974055 Sammlung Knecht\n", + "knecht Q114719888 Rokende mannen in een schuur, met een officier en een knecht op de voorgrond\n", + "knecht Q1237356 knecht\n", + "knecht Q17275857 Hopman Ulrich of de bedrogen gierigheid: Godefroy en zijn knecht verjagen in vermomminghopman Ulrich\n", + "knecht Q2487928 Belindor en zijn knecht\n", + "knecht Q57507224 Meneer, de knecht en fatalist (1994-1995)\n", + "knecht Q57509271 Arlecchino, knecht zonder meesters (1997-1998)\n", + "koelie Q548135 koelie\n", + "koelies Q104680922 De miljoenen uit Deli, koelies en planters op de tabaksplantages op Oost-Sumatra rond 1900\n", + "lagelonenland Q2639564 lagelonenland\n", + "madras Q6728464 Madras, Mpumalanga\n", + "marron Q108960293 Marron Vrouwen Netwerk\n", + "marron Q6773021 Marron Valley\n", + "marrons Q13747796 grondenrechten van de inheemsen en marrons in Suriname\n", + "marrons Q14632167 Inwijdingsrituelen van Surinaamse Marrons\n", + "marrons Q1903204 Marrons van Suriname\n", + "marrons Q3346785 Nèg' Marrons\n", + "marrons Q445485 marrons\n", + "medicijnman Q110368077 Stoeltje medicijnman\n", + "medicijnman Q110368731 Staf medicijnman\n", + "medicijnman Q13430620 Arts en medicijnman\n", + "medicijnman Q266750 medicijnman\n", + "medicijnman Q28106968 Medicijnman\n", + "mesties Q110055515 Spanjaard en mesties, kasteschilderij\n", + "metis Q190565 Metis\n", + "metis Q22699415 Metis Island\n", + "metis Q62033842 Bureau Vrouwenhulpverlening Nederland Metis\n", + "metis Q89197458 Friskolan Metis\n", + "metis Q89903220 Friskolan Metis\n", + "mohammedanen Q114708177 Mohammedanen gaan een moskee binnen\n", + "mongolen Q1740683 Khoshut-Mongolen\n", + "mongolen Q26235 Chahar-Mongolen\n", + "mongolen Q41975 Mongolen\n", + "mongolen Q469930 De geheime geschiedenis van de Mongolen\n", + "mongolen Q689831 Oirat-Mongolen\n", + "mongolen Q842323 Khalkha-Mongolen\n", + "mongools Q207912 mongools ras\n", + "mongools Q6399808 Chalcha-Mongools\n", + "mongools Q9246 Mongools\n", + "moor Q5188069 Crosland Moor\n", + "moor Q889885 Bodmin Moor\n", + "moor Q5643661 Halton Moor\n", + "moor Q6908024 Moor Allerton\n", + "moor Q28406634 Harden Moor\n", + "moor Q4849340 Bakestone Moor\n", + "moor Q55594749 Bottom o' th' Moor\n", + "moor Q7855578 Turlin Moor\n", + "moren Q169260 Moren\n", + "métis Q262457 Métis\n", + "neger Q21280574 Portret van een jonge vrouw kijkend in een door een neger omhoog gehouden spiegel\n", + "neger Q2196236 De neger van de Narcissus\n", + "neger Q28060300 Portret van een jager met neger en honden\n", + "neger Q55056867 der Neger\n", + "neger Q57507811 Robinson Crusoë, de vrouw en de neger (2005-2006)\n", + "neger Q61857058 Neger\n", + "negers Q57510667 De Negers (2004-2005)\n", + "ontdekken Q28061580 Diana en haar nimfen ontdekken de zwangerschap van Callisto\n", + "ontdekken Q29846151 De dochters van Cecrops ontdekken Eurichtonius\n", + "ontdekken Q22990325 Jeremy Kasdin: Het bloemvormige sterrenscherm dat ons Aarde-achtige planeten laat ontdekken\n", + "ontdekken Q23419078 Aomawa Shields: Hoe we buitenaards leven kunnen ontdekken\n", + "ontdekken Q22988142 Nathan Wolfe: Wat valt er nog te ontdekken?\n", + "ontdekken Q23663987 Chieko Asakawa: Hoe nieuwe technologie blinde mensen de wereld helpt ontdekken\n", + "ontwikkelingslanden Q2180237 Centrum tot Bevordering van de Import uit ontwikkelingslanden\n", + "page Q965204 Handley Page\n", + "pages Q27033121 Groepsportret van vier prinsen van Nassau met pages\n", + "politionele actie Q3309962 politionele actie\n", + "politionele actie Q35200609 Pré-Politionele Actie in Palembang\n", + "politionele acties Q278039 Politionele acties\n", + "primitief Q110734758 primitief leven\n", + "primitief Q2242450 primitief kubisch\n", + "primitieve Q100341316 Primitieve kunst- Etnografica, Cultuur en Acculturatie in Afrika\n", + "primitieve Q17307164 Huis met gevel op aardige houten pui, bekroond door een veel latere primitieve lijst\n", + "primitieve Q2864736 Primitieve kunst\n", + "primitieve Q83781188 Primitieve cultuur\n", + "primitivisme Q848365 primitivisme\n", + "pygmeeën Q100341834 Zij zien door de bomen het bos: Baka-pygmeeën tussen verleden en heden (2006-heden)\n", + "pygmeeën Q171927 Pygmeeën\n", + "pygmeeën Q98121325 onderzoek Pygmeeën (1933)\n", + "queer Q100938988 Conexión Queer: Revista Latinoamericana y Caribeña de Teologías Queer\n", + "queer Q110854357 QUEER\n", + "queer Q1563086 queer theologie\n", + "queer Q58459677 Contemporary lesbian genders : a queer/sociological approach\n", + "queer Q9031850 Queer geschiedenismaand\n", + "queer Q92867534 Handi-Queer\n", + "queer Q98929208 queer studies\n", + "queer Q104775895 Black Queer & Trans Resistance Netherlands\n", + "ras Q3254959 menselijk ras\n", + "ras Q8448318 Categorie:Fictief menselijk ras\n", + "ras Q4829793 Awanat, Ras al-Khaimah\n", + "ras Q4903978 Bida, Ras al-Khaimah\n", + "ras Q7489756 Shariyah, Ras al-Khaimah\n", + "slaaf Q22893595 voortvluchtige slaaf\n", + "slaven Q199898 Slaven\n", + "slaven Q211052 Oostelijke Slaven\n", + "slaven Q2378782 Vroege Slaven\n", + "stam Q133311 stam\n", + "stam Q4295650 Hersteld Apostolische Zendingkerk - Stam Juda\n", + "stammen Q604819 Stammen van Galway\n", + "trans Q2395922 Trans-Atlantische telegraafkabel\n", + "trans Q15873930 cis-trans-selectiviteit\n", + "trans Q2168394 Tepavia Trans\n", + "trans Q3266746 Trans-cinnamate 2-monooxygenase\n", + "trans Q3289959 Trans-Atlantische Vrijhandelszone\n", + "trans Q3008357 Trans-1,2-dihydrobenzene-1,2-diol dehydrogenase\n", + "trans Q3266598 Trans-acenaphthene-1,2-diol dehydrogenase\n", + "trans Q1436339 Trans-cinnamate 4-monooxygenase\n", + "trans Q3133248 trans-2-enoyl-CoA reductase\n", + "tweede wereld Q233472 tweede wereld\n", + "tweede wereld Q2358362 Tweede wereld\n", + "wester Q9337845 Wester-Spätinge\n", + "westerse Q100341852 Westerse beeldvorming over niet-westerse culturen van 1880-2002\n", + "westerse Q11416778 Sjabloon:Navigatie generaties westerse wereld\n", + "westerse Q15925549 culturele generatie van de westerse samenleving\n", + "westerse Q160381 westerse wereld\n", + "westerse Q478958 westerse cultuur\n", + "wit Q17142367 Wit\n", + "wit Q6933946 wit haar\n", + "wit Q6317517 Categorie:Mens en maatschappij in Wit-Rusland\n", + "witte Q20931979 De Witte van Zichem\n", + "witte Q2436251 Kate Witte\n", + "witte Q6674339 witte wieven\n", + "zigeuners Q100340717 Er wonen een heleboel mensen in Nederland, over Turken, Surinamers, Zigeuners en Nederlanders: de multiculturele samenleving die Nederland aan het worden is\n", + "zigeuners Q50308628 Landschap met jagers bij een groep zigeuners\n", + "zigeuners Q5455956 De Vijf en het geheim van de zigeuners\n", + "zigeuners Q61863123 Heuvellandschap met ruiters en vissers bij een bruggetje en een groepje zigeuners rond een vuur\n", + "zigeuners Q64446226 Landschap met wandelaars en zigeuners bij een dorp, 1624 gedateerd\n", + "zuid-rhodesië Q145425 Zuid-Rhodesië op de Olympische Zomerspelen 1928\n", + "zuid-rhodesië Q2448416 Zuid-Rhodesië op de Olympische Zomerspelen 1960\n", + "zuid-rhodesië Q2583467 Zuid-Rhodesië op de Olympische Zomerspelen 1964\n", + "zuid-rhodesië Q41978630 Categorie:VN-resolutie over de weigering van sommige landen om de sancties tegen Zuid-Rhodesië in te stellen\n", + "zuid-rhodesië Q750583 Zuid-Rhodesië\n", + "zuid-rhodesië Q8497313 Categorie:Gouverneur van Zuid-Rhodesië\n", + "zwart Q1922956 zwart haar\n", + "zwarte Q28648434 zwarte Ewald\n", + "zwarte Q49836450 Taferelen uit het leven van de jager: landschap met apen door twee zwarte mannen bespied\n", + "zwarte Q83472612 Allegorie op de smaak met een jonge man in een zwarte jas met een pasglas in de hand\n", + "zwarten Q817393 zwarten\n" + ] + } + ], + "source": [ + "# prefLabel no markers\n", + "case_1 = []\n", + "case_1_count = 0\n", + "for term, hits in wd_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"prefLabel\":\n", + " if hit[\"QID\"] not in e_wd_implicit and hit[\"QID\"] not in e_wd_explicit:\n", + " case_1_count += 1\n", + " case_1.append(hit[\"QID\"])\n", + " print(term, hit[\"QID\"], hit[\"prefLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "309" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_1_count" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/wd_{lang}_case1.txt\",'w') as txt_file:\n", + " for l in case_1:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "blank Q107405878 Blank en wit in de Nederlandse taal\n", + "blanke Q698752 blanke suprematie\n", + "dwerg Q2419953 dwerg\n", + "inuit Q189975 Inuit\n", + "jap Q1192767 Jap\n", + "kaffer Q1285250 Kaffer\n", + "page Q855855 page\n", + "queer Q51415 queer\n", + "ras Q7129609 Kaukasisch ras\n", + "ras Q989255 ras in werk van Tolkien\n", + "slaaf Q12773225 tot slaaf gemaakte\n", + "zigeuner Q76475 zigeuner\n" + ] + } + ], + "source": [ + "# prefLabel with markers\n", + "case_1_markers = []\n", + "case_1_markers_count = 0\n", + "for term, hits in wd_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"prefLabel\":\n", + " # either markers\n", + " if hit[\"QID\"] in e_wd_implicit or hit[\"QID\"] in e_wd_explicit:\n", + " case_1_markers_count += 1\n", + " case_1_markers.append(hit[\"QID\"])\n", + " print(term, hit[\"QID\"], hit[\"prefLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "12" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_1_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/wd_{lang}_case1_with_markers.txt\",'w') as txt_file:\n", + " for l in case_1_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 2" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginals Q170355 ['Aboriginals', 'Australiden', 'Aboriginal', 'austraalnegers']\n", + "aboriginals Q216839 ['Taiwanese aboriginals']\n", + "afkomst Q1642895 ['afkomst', 'afstamming', 'nakomeling']\n", + "afkomst Q423803 ['Kantonese afkomst']\n", + "afkomst Q45315 ['Tamazgha', 'Berberse wereld', 'Berberse afkomst', 'Berberse taal', 'Imazighen', 'Amazigh']\n", + "afkomst Q905761 ['afkomst van de vogels']\n", + "allochtoon Q492145 ['excuusneger', 'Token allochtoon']\n", + "baboe Q936969 ['Baboe', 'Kindermeid', 'Kindermeisje']\n", + "batavia Q110409649 ['Topografische dienst in Nederlandsch-Indië', 'Topografische dienst in Nederlands-Indië', 'Topographischen Dienst in Nederlandsch Indië', 'Topografische Dienst Batavia', 'Topografische Dienst van Nederlands Indië.']\n", + "batavia Q1199713 ['Batavia (Nederlands-Indie)']\n", + "batavia Q84322891 ['Gouvernements Filmbedrijf Multifilm Batavia', 'Multifilm, Batavia']\n", + "batavia Q84322891 ['Gouvernements Filmbedrijf Multifilm Batavia', 'Multifilm, Batavia']\n", + "bediende Q833860 ['bediende', 'huishoudster', 'dienstmaagd']\n", + "berber Q21143451 ['Berber (voornaam)']\n", + "birma Q836 ['Birma', 'MMR', 'MM']\n", + "bombay Q1156 ['Mombai', 'Mombay', 'Mumbay', 'Bombai', 'Bombay']\n", + "bombay Q61445 ['New Bombay', 'Nieuw-Bombay']\n", + "bombay Q61445 ['New Bombay', 'Nieuw-Bombay']\n", + "boslandcreool Q445485 ['maroon', 'boslandcreool', 'bosneger', 'marons', 'bosnegers']\n", + "bosnegers Q445485 ['maroon', 'boslandcreool', 'bosneger', 'marons', 'bosnegers']\n", + "dwerg Q194101 ['dwerg']\n", + "etniciteit Q41710 ['etniciteit', 'bevolkingsgroep', 'etnisch', 'etnische bevolking']\n", + "etniciteit Q851126 ['Gorani (etniciteit)']\n", + "gay Q104969456 ['homoseksueel', 'homo', 'gay']\n", + "gay Q1496534 ['Gay (voornaam)']\n", + "gay Q189758 ['Marvin P. Gaye', 'Marvin Pentz Gay, Jr.']\n", + "gay Q958953 ['Jean-Baptiste Sylvere Gaye de Martignac', 'Jean Baptiste Gay de Martignac', 'Conde de Martignac']\n", + "gay Q12012782 ['gay docking', 'cock docking']\n", + "gehandicapte Q15978181 ['gehandicapt persoon', 'invalide', 'persoon met een beperking', 'gehandicapte persoon', 'persoon met een handicap']\n", + "gehandicapte Q183560 ['Zwakzinnigheid', 'Verstandelijk gehandicapte', 'Retardatie', 'mentale handicap', 'verstandelijke handicap', 'verstandelijk gehandicapt', 'zwakzinnig', 'idioot', 'mentale retardatie']\n", + "gehandicapte Q90665701 ['Wet zorg en dwang psychogeriatrische en verstandelijk gehandicapte cliënten', 'Wzd']\n", + "gehandicapten Q2423714 ['Chronisch zieken en Gehandicapten Raad Nederland']\n", + "handicap Q183560 ['Zwakzinnigheid', 'Verstandelijk gehandicapte', 'Retardatie', 'mentale handicap', 'verstandelijke handicap', 'verstandelijk gehandicapt', 'zwakzinnig', 'idioot', 'mentale retardatie']\n", + "handicap Q183560 ['Zwakzinnigheid', 'Verstandelijk gehandicapte', 'Retardatie', 'mentale handicap', 'verstandelijke handicap', 'verstandelijk gehandicapt', 'zwakzinnig', 'idioot', 'mentale retardatie']\n", + "hermafrodiet Q16674976 ['hermafroditisme', 'hermafrodiet']\n", + "homo Q104969456 ['homoseksueel', 'homo', 'gay']\n", + "homo Q5 ['Homo sapiens', 'mensen', 'Mens']\n", + "homo Q849216 ['ex-homo']\n", + "homo Q131464 ['Rhodesië man', 'Rhodesie man', 'Homo rhodesiensis', 'Rhodesiemens']\n", + "homoseksueel Q40221 ['Homoseksueel icoon']\n", + "homoseksueel Q592 ['homoseksueel persoon']\n", + "homoseksuele Q110271724 ['Lesbische vrouw', 'Homoseksuele vrouw']\n", + "hottentotten Q219252 ['Hottentot', 'Khoi', 'Hottentotten']\n", + "indiaans Q36747 ['Indianenstam', 'Indiaanse', 'Indiaans', 'Oorspronkelijke Amerikanen', 'Roodhuid', 'inheemse Amerikaanse indianen', 'Amerikaanse indianen', 'inheemse indianen']\n", + "indianen Q1261048 ['Warao-indianen', 'Waraos']\n", + "indianen Q6034885 ['Surinaamse indianen']\n", + "indisch Q188161 ['Nederlands Indië', 'Nederlandsch-Indie', 'Nederlands Indie', 'Nederlands Oost-Indië', 'De Oost', 'Nederlands-Indisch', 'Nederland overzee', 'Hindia-Belanda', 'Nederlands-Indie', 'Nederlandsch-Indië', 'Nederlands Oost-Indie']\n", + "indisch Q215643 ['Indo-Griekse Rijk', 'Indo-Grieks koninkrijk', 'Indo-Grieks', 'Indisch-Griekse koninkrijk', 'Indisch-Grieks koninkrijk']\n", + "indisch Q215643 ['Indo-Griekse Rijk', 'Indo-Grieks koninkrijk', 'Indo-Grieks', 'Indisch-Griekse koninkrijk', 'Indisch-Grieks koninkrijk']\n", + "indische Q53034861 ['Wet tot opheffing der slavernij in de Nederlandsche West-Indische Koloniën']\n", + "indo Q215643 ['Indo-Griekse Rijk', 'Indo-Grieks koninkrijk', 'Indo-Grieks', 'Indisch-Griekse koninkrijk', 'Indisch-Grieks koninkrijk']\n", + "indo Q215643 ['Indo-Griekse Rijk', 'Indo-Grieks koninkrijk', 'Indo-Grieks', 'Indisch-Griekse koninkrijk', 'Indisch-Grieks koninkrijk']\n", + "indo Q215643 ['Indo-Griekse Rijk', 'Indo-Grieks koninkrijk', 'Indo-Grieks', 'Indisch-Griekse koninkrijk', 'Indisch-Grieks koninkrijk']\n", + "indo Q475027 ['Indogermanen', 'Indo-Germanen', 'Indo-Europese volkeren', 'Indo-Europese volken']\n", + "indo Q475027 ['Indogermanen', 'Indo-Germanen', 'Indo-Europese volkeren', 'Indo-Europese volken']\n", + "indo Q475027 ['Indogermanen', 'Indo-Germanen', 'Indo-Europese volkeren', 'Indo-Europese volken']\n", + "indo's Q2116909 ['Indo-Europeanen', \"Indo's\", 'Indische gemeenschap']\n", + "inheemse Q103817 ['Natives', 'oorspronkelijke bewoners', 'inheemsen', 'oorspronkelijke bevolking', 'inheemse volken', 'inheems volk', 'inheemse volkeren', 'primitieve volkeren', 'oorspronkelijke culturen']\n", + "inheemse Q103817 ['Natives', 'oorspronkelijke bewoners', 'inheemsen', 'oorspronkelijke bevolking', 'inheemse volken', 'inheems volk', 'inheemse volkeren', 'primitieve volkeren', 'oorspronkelijke culturen']\n", + "inheemse Q15571255 ['inheemse bevolking van Noord-Amerika']\n", + "inheemse Q36747 ['Indianenstam', 'Indiaanse', 'Indiaans', 'Oorspronkelijke Amerikanen', 'Roodhuid', 'inheemse Amerikaanse indianen', 'Amerikaanse indianen', 'inheemse indianen']\n", + "inheemse Q36747 ['Indianenstam', 'Indiaanse', 'Indiaans', 'Oorspronkelijke Amerikanen', 'Roodhuid', 'inheemse Amerikaanse indianen', 'Amerikaanse indianen', 'inheemse indianen']\n", + "inlander Q1945590 ['Inlander (Nederlands-Indie)']\n", + "inuit Q1128374 ['Inuitgemeenschap', 'Inuit Ataqatigiit-partij']\n", + "inuit Q888553 ['Groenlandse Inuit']\n", + "islamieten Q47740 ['Mohameddanen', 'Mohammedaan', 'Moeslim', 'Mohammedanen', 'Moslima', 'Islamieten', 'Islamiet', 'Moslem', 'Moslims']\n", + "jap Q161652 ['Japanner', 'Jap', 'Japanse beschaving', 'Japanse bevolking']\n", + "jappenkampen Q2432369 ['Jappenkampen in Nederlands-Indie']\n", + "kaukasische Q169921 ['Kaukazische talen', 'Kaukasische taal']\n", + "kaukasische Q2088141 ['Kaukasische imamaat', 'Kaukasische lmamaat']\n", + "kaukasische Q2088141 ['Kaukasische imamaat', 'Kaukasische lmamaat']\n", + "kaukasische Q330756 ['Trans-Kaukasische Federatieve Democratische Republiek', 'Trans-Kaukasische Federatieve Republiek', 'Kaukasische Federatie', 'Trans-Kaukasische Federatie', 'Transkaukasische Federatie']\n", + "kaukasische Q330756 ['Trans-Kaukasische Federatieve Democratische Republiek', 'Trans-Kaukasische Federatieve Republiek', 'Kaukasische Federatie', 'Trans-Kaukasische Federatie', 'Transkaukasische Federatie']\n", + "kaukasische Q330756 ['Trans-Kaukasische Federatieve Democratische Republiek', 'Trans-Kaukasische Federatieve Republiek', 'Kaukasische Federatie', 'Trans-Kaukasische Federatie', 'Transkaukasische Federatie']\n", + "kaukasische Q330756 ['Trans-Kaukasische Federatieve Democratische Republiek', 'Trans-Kaukasische Federatieve Republiek', 'Kaukasische Federatie', 'Trans-Kaukasische Federatie', 'Transkaukasische Federatie']\n", + "knecht Q108839849 ['Helen M. Drenth', 'Helen M. Drenth-Knecht', 'Helen Drenth-Knecht']\n", + "knecht Q108839849 ['Helen M. Drenth', 'Helen M. Drenth-Knecht', 'Helen Drenth-Knecht']\n", + "knecht Q5060555 ['knecht', 'landarbeider']\n", + "madras Q1352 ['Madras']\n", + "marron Q16735433 ['Javier Marron Jimenez']\n", + "marron Q1709371 ['Jose Luis Vallarta Marron']\n", + "medicijnman Q42042 ['medicijnman', 'sjamanen', 'shamanisme']\n", + "mestiezen Q106713 ['Mestiezen']\n", + "mohammedanen Q47740 ['Mohameddanen', 'Mohammedaan', 'Moeslim', 'Mohammedanen', 'Moslima', 'Islamieten', 'Islamiet', 'Moslem', 'Moslims']\n", + "mongolen Q689831 ['Oirot', 'Oirot-Mongolen']\n", + "mongools Q1055705 ['Mongools alfabet', 'Mongools schrift']\n", + "mongools Q1055705 ['Mongools alfabet', 'Mongools schrift']\n", + "métis Q110068902 ['Métis']\n", + "neger Q18574018 ['Neger met papegaaien en apen']\n", + "negers Q17276026 ['Twee negers', 'Twee Afrikaanse mannen']\n", + "ontwikkelingslanden Q16765325 ['Nederlandse Financierings-Maatschappij voor Ontwikkelingslanden']\n", + "ontwikkelingslanden Q177323 ['ontwikkelingslanden', 'derdewereldland']\n", + "ontwikkelingslanden Q47486214 ['Aangepaste Technologie in Ontwikkelingslanden']\n", + "pages Q786613 ['Salvador Casanas y Pages']\n", + "pages Q9053105 ['Oriol Regas i Pages']\n", + "pages Q16163906 ['Trinitat Aldrich i de Pages', 'Trinidad Aldrich de Pagés']\n", + "pages Q1891649 ['Manuel Pages i Mercader']\n", + "pages Q11919228 ['Emilia Xargay i Pages']\n", + "politionele actie Q35200609 ['Pre-Politionele Actie in Palembang']\n", + "primitief Q1937269 ['Primitief kenmerk', 'Primitief']\n", + "primitief Q1937269 ['Primitief kenmerk', 'Primitief']\n", + "primitivisme Q667672 ['anarcho-primitivisme']\n", + "ras Q3254959 ['Ras', 'mensenras']\n", + "slaven Q199898 ['Slaven (voornaam)']\n", + "stam Q1104182 ['Coahuilteken (stam)', 'Coahuilteken (volk)']\n", + "stam Q2381172 ['stedelijke stam', 'stedelijke clan']\n", + "stam Q250584 ['Morini (stam)']\n", + "stammen Q156108 ['Obotrieten', 'Obodriten', 'Obodriten - Slavische stammen']\n", + "travestiet Q486680 ['travestiet', 'travesti', 'transvestitisme']\n", + "tweede wereld Q2358362 ['Tweede wereld (Thorgal)']\n", + "wit Q163800 ['Veit Stoß', 'Wit Stwosz']\n", + "wit Q17142367 ['Wit (voornaam)']\n", + "witte Q235155 ['witte mensen']\n", + "witte Q55677536 ['Bertram Witte']\n", + "witte Q113457800 ['Sascha Witte']\n", + "zigeuner Q110158779 ['Zigeuner architectuur']\n", + "zigeuners Q106133380 ['Woonwagenbewoners', 'Zigeuners']\n", + "zigeuners Q117571 ['Samudaripen', 'Vernietiging van de zigeuners tijdens de Tweede Wereldoorlog', 'Porajmos', 'Vernietiging van de Roma tijdens de Tweede Wereldoorlog', 'Vervolging van de zigeuners tijdens de Tweede Wereldoorlog', 'Porrajmos', 'Roma-vervolging in het Derde Rijk']\n", + "zigeuners Q117571 ['Samudaripen', 'Vernietiging van de zigeuners tijdens de Tweede Wereldoorlog', 'Porajmos', 'Vernietiging van de Roma tijdens de Tweede Wereldoorlog', 'Vervolging van de zigeuners tijdens de Tweede Wereldoorlog', 'Porrajmos', 'Roma-vervolging in het Derde Rijk']\n", + "zigeuners Q371762 ['Witte Zigeuners']\n", + "zwart Q18434892 ['Saskia Zwart-Boelsums', 'S. Zwart-Boelsums']\n", + "zwart Q18434892 ['Saskia Zwart-Boelsums', 'S. Zwart-Boelsums']\n", + "zwart Q1922956 ['zwart (haarkleur)']\n", + "zwarte Q107094905 ['De Zwarte Hen', 'Adam Meyer']\n", + "zwarte Q734967 ['Kara-Iskaki (zwarte Jacob)']\n" + ] + } + ], + "source": [ + "# altLabel no markers\n", + "case_2 = []\n", + "case_2_count = 0\n", + "for term, hits in wd_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"aliases\":\n", + " if hit[\"QID\"] not in e_wd_implicit and hit[\"QID\"] not in e_wd_explicit:\n", + " case_2_count += 1\n", + " case_2.append(hit[\"QID\"])\n", + " print(term, hit[\"QID\"], hit[\"aliases\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "125" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_2_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/wd_{lang}_case2.txt\",'w') as txt_file:\n", + " for l in case_2:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "barbaren Q134313 ['barbaren', 'barbaars']\n", + "kaukasische Q7129609 ['Kaukasische ras']\n", + "lilliputter Q2419953 ['lilliputter']\n", + "mulatten Q191923 ['Mulattin', 'Mulatten']\n", + "negers Q1130557 ['negroide ras', 'negers', 'negroïde ras', 'negroide', 'negerinnen', 'nigga', 'negroïde', 'negerin']\n", + "ras Q7129609 ['Kaukasische ras']\n", + "slaaf Q12773225 ['slaaf', 'slaafgemaakte']\n" + ] + } + ], + "source": [ + "# altLabel with markers\n", + "case_2_markers = []\n", + "case_2_markers_count = 0\n", + "for term, hits in wd_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"aliases\":\n", + " # either markers\n", + " if hit[\"QID\"] in e_wd_implicit or hit[\"QID\"] in e_wd_explicit:\n", + " case_2_markers_count += 1\n", + " case_2_markers.append(hit[\"QID\"])\n", + " print(term, hit[\"QID\"], hit[\"aliases\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "7" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_2_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/wd_{lang}_case2_with_markers.txt\",'w') as txt_file:\n", + " for l in case_2_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 3" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal Q254387 inheemse minderheden van het schiereiland Maleisië; verzamelnaam voor de 18 etnische subgroepen die officieel voor administratieve doeleinden zijn ingedeeld onder Negrito, Senoi en Aboriginal Maleis\n", + "aboriginal Q1476490 scheppergod en motief in de kunst en religie van Aboriginal Australië\n", + "aboriginals Q111248029 jonge Manbarra-vrouw die samen met acht andere Aboriginals op etnologische tentoonstellingen in Amerika en Europa werd ‘geëxposeerd’\n", + "aboriginals Q1492906 etnische groep Aboriginals in Zuidoost-Australië, bij Melbourne\n", + "afkomst Q110903593 etnische groep; Fransen van Rwandese afkomst\n", + "afkomst Q12332701 discriminatie op grond van ras, huidskleur, afkomst of nationale of etnische afstamming\n", + "afkomst Q3023540 multiraciale historica van Chinees-Amerikaanse afkomst (1885-1944)\n", + "afkomst Q60741209 etnische groep in Nieuw-Zeeland van mensen met gemengde Māori en Indiase afkomst\n", + "batavia Q2558220 voorstad van Batavia\n", + "batavia Q4868680 ziekenhuis in Batavia, Verenigde Staten van Amerika\n", + "batavia Q66737952 vervoersbedrijf in Batavia\n", + "batavia Q98550142 Vereeniging De Nederlands-Indische kunstkring in Batavia\n", + "bediende Q106075658 bediende Tsjechoslowaakse ministerie van Binnenlandse Zaken (1892-1978)\n", + "bediende Q106246935 bediende in Wien, postdirecteur en financiële inspecteur in Praag (1862-1924)\n", + "bediende Q106686255 bediende en directeur Slowaakse sociale verzekering (fl. 1924-41)\n", + "bediende Q106737573 bediende ministerie van binnenlandse zaken in Praag (1884-1958)\n", + "bediende Q106767195 Tsjechische bediende financiële administratie (1860-??)\n", + "bediende Q99228228 bediende van belastingdienst in Praag, expert in distilleerderijen\n", + "blank Q2072081 persoon die niet blank/wit is\n", + "blank Q107405878 betreft de discussie of het gebruik van de term 'blank' racistisch is\n", + "blanken Q111545624 praktijk waarbij blanken mensen gebruikmaken van GIF's en digitale afbeeldingen van zwarte mensen voor zelfexpressie\n", + "blanken Q50878538 boreaal kan in de politiek soms gebruikt worden als eufemisme voor 'enkel door blanken bevolkt'\n", + "bombay Q12413015 buitenwijk in Bombay, India\n", + "bombay Q1934607 wijk in Bombay, India\n", + "bombay Q3632559 wijk in Bombay, India\n", + "bombay Q4856518 buitenwijk in Bombay, India\n", + "bombay Q5003979 wijk in Bombay, India\n", + "bombay Q7685715 wijk in Bombay, India\n", + "bombay Q5100150 wijk in Bombay, India\n", + "calcutta Q67906158 straat in Calcutta, India\n", + "calcutta Q67911834 straat in Calcutta, India\n", + "calcutta Q77425397 straat in Calcutta, India\n", + "calcutta Q5328741 wijk in Calcutta, India\n", + "calcutta Q67652597 straat in Calcutta, India\n", + "calcutta Q68159535 straat in Calcutta, India\n", + "calcutta Q68647181 straat in Calcutta, India\n", + "calcutta Q7567630 wijk in Calcutta\n", + "eskimo Q4532729 Wetenschap van de taal, literatuur en cultuur van de Eskimo (Inuit)\n", + "eskimo's Q189975 naam waarmee de Eskimo's van Groenland en Canada zichzelf aanduiden\n", + "etniciteit Q110891832 inwoners of mensen van Tahiti, Frans-Polynesië, ongeacht etniciteit\n", + "etniciteit Q111654081 inwoners of staatsburgers van Kroatië, ongeacht etniciteit\n", + "etniciteit Q115771874 mensen uit of inwoners van Hongarije, ongeacht etniciteit\n", + "etniciteit Q133032 een nationaliteit en een etniciteit in hoofdzakelijk Centraal-Europa\n", + "etniciteit Q7325 aanhangers van de joodse religie (joden) dan wel iemand met de joodse etniciteit (Joden)\n", + "etniciteit Q8461 op ras of etniciteit gebaseerde discriminatie\n", + "etniciteit Q851126 etniciteit\n", + "etnische groep Q12223 etnische groep\n", + "etnische groep Q154278 gewelddadige actie om de aanwezigheid etnische groep in een gebied te doen dalen\n", + "etnische groep Q16513600 de plaats waar een etnische groep zich cultureel en historisch mee identificeert\n", + "etnische groep Q1988847 etnische groep\n", + "etnische groep Q3502570 etnische groep\n", + "etnische groep Q3676128 etnische groep\n", + "etnische groep Q533226 etnische groep\n", + "gekleurd Q506 vaak fraai gekleurd voortplantingsorgaan van bedektzadige planten\n", + "gekleurde Q133067 een grote afbeelding wordt vervaardigd uit een groot aantal kleine gekleurde steentjes\n", + "gekleurde Q6544309 gekleurde banden van cement in sedimentair gesteente\n", + "gekleurde Q739550 snoepjes van Amerikaanse oorsprong van chocolade met een gekleurde buitenlaag\n", + "handicap Q114572905 astronaut met een lichamelijke handicap\n", + "handicap Q13635220 in Vlaanderen voor kinderen die het gewone onderwijs niet kunnen volgen vanwege leer- of gedragsproblemen of vanwege een lichamelijke, zintuiglijke of verstandelijke handicap\n", + "handicap Q264231 persoon die plaatselijk bekend staat om excentriciteit of een mentale handicap\n", + "homo Q105784 soort uit het geslacht Homo\n", + "homo Q54882501 cellijn van een Homo sapiens\n", + "homo Q131464 soort uit het geslacht Homo\n", + "homo Q54882504 cellijn van een Homo sapiens\n", + "homo Q54993583 cellijn van een Homo sapiens\n", + "homoseksualiteit Q1054678 Het naar buiten brengen iemands seksuele voorkeur, in het bijzonder homoseksualiteit\n", + "homoseksualiteit Q27333507 Homoseksualiteit in Koerdistan\n", + "homoseksueel Q2335529 afkorting voor homoseksueel, lesbisch en biseksueel\n", + "homoseksueel Q6649 vrouwelijk homoseksueel\n", + "homoseksuele Q16154286 pogingen om de seksuele geaardheid van homoseksuele mensen te veranderen\n", + "indianen Q3323096 is een type forten en militaire buitenposten die door de Spanjaarden tussen de 16e en 19e eeuw in Noord-Amerika opgericht werden. Presidio's werden gebouwd als bescherming tegen piraten, gewelddadige indianen en vijandige kolonisten.\n", + "indianen Q510048 Indianen, oorspronkelijke bewoners van Noord-Amerika\n", + "indische Q109712735 Nederlands-Indische Amerikaanse expeditie naar Nieuw-Guinea\n", + "indische Q100341062 rondreizende Indische tentoonstelling en filmvoorstellingen voor de Nederlandse jeugd\n", + "indo Q1610219 westelijke Indo-Griekse koning van de Eucratiden-dynastie die over het gebied van de Paropamisade in de Hindoekoesj heerste, met als hoofdstad Alexandria van de Kaukasus bij het huidige Kabul, Afghanistan\n", + "indo Q40477 de Indo-Europese volken die een taal uit de Slavische taalfamilie spreken en worden aan de hand van de onderverdeling van deze taalfamilie onderscheiden in Oost-, West- en Zuid-Slaven\n", + "indo Q8752 niet-Indo-Europese taal isolaat gesproken door de Baskische bevolking in delen van het huidige Frankrijk en Spanje\n", + "indo Q269145 theorie van migraties van Indo-Arische volkeren naar het Indisch Subcontinent\n", + "inheemse Q16908608 inheemse bevolking\n", + "inheemse Q1755300 Vervanging van de Westerse inheemse bevolking door immigranten met een niet-Westerse cultuur\n", + "inheemse Q804127 inheemse groep afkomstig van het eiland Bajau in het regentschap Anambas-eilanden, provincie Riau-eilanden, Indonesië\n", + "inuit Q4532729 Wetenschap van de taal, literatuur en cultuur van de Eskimo (Inuit)\n", + "jappenkamp Q62498853 voormalig jappenkamp voor burgers\n", + "jappenkamp Q71859469 Jappenkamp gevestigd rond het Algemeen Delisch Emigratie-Kantoor\n", + "kaukasisch Q2096913 monarch uit Kaukasisch Iberië (?-216)\n", + "kaukasisch Q2655106 staatshoofd uit Kaukasisch Iberië (-132)\n", + "knecht Q108839781 kunstwerken verzameld door het echtpaar Helen Drenth en Tijmen Knecht\n", + "madras Q3133187 buitenwijk in Madras, India\n", + "madras Q3530475 buitenwijk in Madras, India\n", + "madras Q3534941 buitenwijk in Madras, India\n", + "madras Q3537400 buitenwijk in Madras, India\n", + "madras Q4738370 wijk in Madras, India\n", + "madras Q5148870 buitenwijk in Madras, India\n", + "madras Q4746424 wijk in Madras, India\n", + "madras Q6932073 buitenwijk in Madras, India\n", + "marron Q110347727 begraafplaats in Yvoy-le-Marron, Frankrijk\n", + "medicijnman Q26822103 medicijnman\n", + "medicijnman Q77046403 Amerikaans medicijnman (1887-1980)\n", + "moren Q2636673 stad exclusief bezet door Moren of Joden of wijk van de christelijke stad bezet door deze etnische groepen in de Middeleeuwen\n", + "métis Q5515604 academisch instituut Métis in Saskatchewan, Canada\n", + "ontdekken Q1646902 met opzet toegevoegde nepgegevens om plagiaat te ontdekken\n", + "ontwikkelingsland Q4966238 privéschool in ontwikkelingsland\n", + "ontwikkelingslanden Q352378 organisatie voor financiering van klimaatvriendelijke projecten in ontwikkelingslanden\n", + "ontwikkelingslanden Q75042240 lector algemene sociologie, in het bijzonder de sociologie van de ontwikkelingslanden Tilburg\n", + "ontwikkelingslanden Q7937037 Nederlandse non-profit organisatie voor schoon drinkwater in ontwikkelingslanden\n", + "ontwikkelingslanden Q865909 programma's ter verbetering van de politieke, economische en sociale situatie in de ontwikkelingslanden\n", + "pages Q944818 geslacht uit de familie pages\n", + "pages Q556018 geslacht uit het familie pages (Papilionidae)\n", + "primitieve Q1350206 Primitieve van 1/ln\n", + "primitieve Q5202866 primitieve bouwtechniek\n", + "primitieve Q93883800 fictief personage uit het boek De stam van de Holenbeer, vader van Goov. De beste maker van primitieve gereedschappen\n", + "queer Q26936735 dataset met termen voor het beschrijven van LHBTIQ (Lesbisch/Homo/Biseksueel/Transgender/Intersekse/Queer)-publicaties en -erfgoed\n", + "ras Q100474769 gelijke behandeling van personen ongeacht ras of etnische afstamming\n", + "ras Q1571949 esoterische leer dat uitgaat van de superioriteit van het Arische ras\n", + "ras Q59816 het scheiden van mensen op basis van hun veronderstelde ras\n", + "slaaf Q1120876 Frans slaaf (-1880), maar bekend als de uitvinder van het handmatig bestuiven van vanilleplanten\n", + "slaaf Q1830234 slaaf in het bezit van een Spaans slaveneigenaar, die hij vermoordde, waarna hij en zijn volgelingen hun toevlucht zochten op La Tortue\n", + "slaaf Q2159754 in Suriname gebruikelijk benaming voor een zware lijfstraf voor tot slaaf gemaakten\n", + "slaven Q1155622 (gewapende) opstand van slaven tegen overheid of plantage-eigenaar\n", + "slaven Q601444 juridisch hoofd van een huishouden in het oude Rome, eigenaar van alle goederen en slaven, uitsluitend mannelijk geslacht\n", + "stam Q250584 stam\n", + "stam Q4955096 onderklasse van kreeftachtigen binnen de stam geleedpotigen\n", + "stam Q5373604 geslacht uit de stam Problematica\n", + "stammen Q11913408 grondgebied van het Iberisch schiereiland waar de Keltiberische stammen leefden\n", + "trans Q94581668 syndicat intercommunal in Trans\n", + "travestiet Q7835451 seksuele voorkeur voor een travestiet als partner\n", + "westerse Q1365619 oorspronkelijk het westelijke deel van Europa, vanaf de 21e eeuw de hele westerse wereld\n", + "westerse Q1637806 voorstellingen van de westerse wereld\n", + "westerse Q1755300 Vervanging van de Westerse inheemse bevolking door immigranten met een niet-Westerse cultuur\n", + "westerse Q42865 westerse opvatting van het Oosten in culturele zin\n", + "zuid-rhodesië Q1425676 politieke partij uit Zuid-Rhodesië\n", + "zuid-rhodesië Q18729864 basisschool in Zuid-Rhodesië\n", + "zuid-rhodesië Q6380582 politicus uit Zuid-Rhodesië (1913-2010)\n", + "zuid-rhodesië Q83689634 journalist uit Zuid-Rhodesië (1886-1960)\n", + "zwart Q1130557 historische term voor zwart persoon\n", + "zwart Q4922530 beelden van een jonge zwart Afrikaanse persoon, vaak afgebeeld als hoofd of buste\n", + "zwarte Q107094905 boek- en papierverkoper Adam Meyer op de Voorburgwal over de onvolmaakte Tooren in de Zwarte Hen\n" + ] + } + ], + "source": [ + "case_3 = []\n", + "case_3_count = 0\n", + "for term, hits in wd_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"description\":\n", + " case_3_count += 1\n", + " case_3.append(hit[\"QID\"])\n", + " print(term, hit[\"QID\"], hit[\"description\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "137" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_3_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/wd_{lang}_case3.txt\",'w') as txt_file:\n", + " for l in case_3:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## AAT" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [], + "source": [ + "lang = \"en\"" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": {}, + "outputs": [], + "source": [ + "# import subset\n", + "with open(f\"/Users/anesterov/reps/LODlit/AAT/aat_{lang}_subset.json\",'r') as jf:\n", + " aat_subset = json.load(jf)" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + ":2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", + " e_aat_implicit = implicit_markers[implicit_markers[\"resource\"] == \"aat\"][implicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n", + ":5: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", + " e_aat_explicit = explicit_markers[explicit_markers[\"resource\"] == \"aat\"][explicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n" + ] + } + ], + "source": [ + "# AAT EN entities with implicit markers\n", + "e_aat_implicit = implicit_markers[implicit_markers[\"resource\"] == \"aat\"][implicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()\n", + "\n", + "# AAT EN entities with explicit markers\n", + "e_aat_explicit = explicit_markers[explicit_markers[\"resource\"] == \"aat\"][explicit_markers[\"lang\"] == lang][\"entity_id\"].to_list()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 1" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "batavia 300012925 Batavia dammar\n", + "black 300449148 Black British\n", + "black 300435249 Black (general, race and ethnicity)\n", + "bombay 300378963 Bombay mastic\n", + "caucasian 300244538 Central Caucasian textile styles\n", + "caucasian 300244674 Baku (Caucasian textile style)\n", + "caucasian 300244539 East Caucasian textile styles\n", + "caucasian 300244536 Caucasian (culture or style)\n", + "caucasian 300244540 South Caucasian textile styles\n", + "caucasian 300411945 North Caucasian (language group)\n", + "dwarf 300041590 dwarf tall clocks\n", + "dwarf 300386950 dwarf planets\n", + "eskimo 300016731 Pre-Columbian Eastern Eskimo styles\n", + "eskimo 300016736 Pre-Columbian Western Eskimo styles\n", + "eskimo 300411929 Eskimo-Aleut (language family)\n", + "ethnicity 300435249 Black (general, race and ethnicity)\n", + "ethnicity 300250435 ethnicity\n", + "gay 300391091 Gay-Lussac alcoholometers\n", + "homo 300265711 Homo sapiens (species)\n", + "homosexuals 300435115 homosexuals (people)\n", + "homosexuals 300435114 male homosexuals\n", + "immigrants 300025844 immigrants\n", + "indian 300018863 Indian (South Asian)\n", + "indigenous 300379660 indigenous people\n", + "inuit 300102550 Labrador Inuit\n", + "inuit 300017458 Netsilik Inuit\n", + "madras 300417391 Madras Art Movement\n", + "maroon 300311173 maroon (color)\n", + "metis 300265512 Metis\n", + "moors 300386886 moors (landforms)\n", + "negro 300393224 Negro spirituals\n", + "pages 300055033 title pages\n", + "primitivism 300056548 primitivism (artistic concept)\n", + "pygmy 300262942 Aka (Pygmy style)\n", + "pygmy 300262938 Bongo (Pygmy style)\n", + "retarded 300014934 retarded hemihydrate plaster\n", + "servants 300435318 butlers (servants)\n", + "servants 300136452 domestics (servants)\n", + "servants 300411753 servants' clothing\n", + "slave 300419276 slave owners\n", + "traditional 300435679 traditional cultural properties\n", + "trans 300022218 Trans-avantgarde\n", + "trans 300411958 Trans-New Guinea (language family)\n", + "tribes 300049946 tribes (kinship groups)\n", + "white 300129784 white (color)\n" + ] + } + ], + "source": [ + "# prefLabel no markers\n", + "case_1 = []\n", + "case_1_count = 0\n", + "for term, hits in aat_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"prefLabel\":\n", + " if hit[\"aat_uri\"] not in e_aat_implicit and hit[\"aat_uri\"] not in e_aat_explicit:\n", + " case_1_count += 1\n", + " case_1.append(hit[\"aat_uri\"])\n", + " print(term, hit[\"aat_uri\"], hit[\"prefLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "45" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_1_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/aat_{lang}_case1.txt\",'w') as txt_file:\n", + " for l in case_1:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "disabled 300025925 intellectually disabled\n", + "eskimo 300017447 Eskimo (culture or style)\n", + "hermaphrodites 300386060 hermaphrodites (people)\n", + "homo 300310690 Homo floresiensis (extinct species)\n", + "immigrants 300443480 undocumented immigrants\n", + "indo 300386794 Indo-European (culture)\n", + "inuit 300017455 Inuit (Canadian Arctic Native style)\n", + "maroon 300443390 Maroon\n", + "native 300017437 Native American\n", + "primitive 300056460 primitive architecture\n", + "primitive 300056500 primitive art\n", + "pygmy 300016430 Pygmy (African culture or style)\n", + "servants 300025874 servants\n" + ] + } + ], + "source": [ + "# prefLabel with markers\n", + "case_1_markers = []\n", + "case_1_markers_count = 0\n", + "for term, hits in aat_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"prefLabel\":\n", + " # either markers\n", + " if hit[\"aat_uri\"] in e_aat_implicit or hit[\"aat_uri\"] in e_aat_explicit:\n", + " case_1_markers_count += 1\n", + " case_1_markers.append(hit[\"aat_uri\"])\n", + " print(term, hit[\"aat_uri\"], hit[\"prefLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "13" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_1_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/aat_{lang}_case1_with_markers.txt\",'w') as txt_file:\n", + " for l in case_1_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 2" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal 300379660 ['indigenous person', 'indigenous peoples', 'aboriginal peoples', 'indigenous populations', 'native peoples', 'aborigines', 'indigenes', 'people, indigenous']\n", + "aboriginal 300404576 ['art, indigenous', 'aboriginal art']\n", + "barbarian 300106913 ['Migration (Medieval culture or period)', 'Dark Ages (Medieval culture or period)', 'Barbarian (Migration culture or period)']\n", + "barbarian 300018585 ['art, namban', 'art, southern barbarian', 'barbarian art, southern', 'namban art', 'southern barbarian art']\n", + "barbarian 300018585 ['art, namban', 'art, southern barbarian', 'barbarian art, southern', 'namban art', 'southern barbarian art']\n", + "barbarian 300018585 ['art, namban', 'art, southern barbarian', 'barbarian art, southern', 'namban art', 'southern barbarian art']\n", + "batavia 300012925 ['Batavia damar', 'dammar, Batavia']\n", + "batavia 300012925 ['Batavia damar', 'dammar, Batavia']\n", + "berber 300263729 ['Chleuh', 'Chleuhs', 'Schluh', 'Shilha', 'Shilhas', 'Shlûh', 'Shluhs', 'Susi (Berber)', 'Susiua (Shluh)', 'Tachelhit', 'Tachilhit', 'Tashelhit', 'Tashelhiyt', 'Tashilhait', 'Tashilheet', 'Tashilhit', 'Tasoussit']\n", + "berber 300375152 ['Maures', 'Moor (culture or style)', 'Mauri (Arab-Berber culture or style)']\n", + "black 300449148 ['British, Black']\n", + "black 300443479 ['black, indigenous and people of color', 'black, indigenous, people of color']\n", + "black 300443479 ['black, indigenous and people of color', 'black, indigenous, people of color']\n", + "bombay 300378963 ['mastic, Bombay', 'Indian mastic']\n", + "bombay 300375341 ['East Indian rosewood (species)', 'Indian rosewood (Dalbergia latifolia, species)', 'Bombay blackwood (species)', 'Java palisander (species)', 'Indian palisandre (species)', 'black rosewood (species)', 'beete (species)', 'sitsal (species)', 'satisal (species)', 'sonokeling (species)', 'sonobrits (species)']\n", + "bombay 300012439 ['Bombay blackwood (wood)', 'rosewood, East Indian (wood)', 'Indian rosewood (Dalbergia latifolia, wood)']\n", + "caucasian 300244538 ['styles, Central Caucasian textile', 'Central Caucasian textile style']\n", + "caucasian 300244538 ['styles, Central Caucasian textile', 'Central Caucasian textile style']\n", + "caucasian 300244539 ['styles, East Caucasian textile', 'East Caucasian textile style']\n", + "caucasian 300244539 ['styles, East Caucasian textile', 'East Caucasian textile style']\n", + "caucasian 300244540 ['styles, South Caucasian textile', 'South Caucasian textile style']\n", + "caucasian 300244540 ['styles, South Caucasian textile', 'South Caucasian textile style']\n", + "developing nations 300379994 ['developing country', 'Third World', 'emerging nations', 'developing nations', 'least-developed countries', 'less-developed countries', 'LDCs', 'countries, developing']\n", + "disabled 300025924 [\"mentally handicapped's\", 'handicapped, mentally', 'mentally disabled']\n", + "disabled 300025926 [\"physically handicapped's\", 'handicapped, physically', 'physically disabled']\n", + "disabled 300000311 ['handicapped, housing for the', 'housing for disabled', 'housing for handicapped', 'housing for physically handicapped', 'housing for the disabled', 'housing for the physically handicapped']\n", + "disabled 300000311 ['handicapped, housing for the', 'housing for disabled', 'housing for handicapped', 'housing for physically handicapped', 'housing for the disabled', 'housing for the physically handicapped']\n", + "disabled 300025921 [\"handicapped's\", 'disabled', 'disabled people']\n", + "disabled 300025921 [\"handicapped's\", 'disabled', 'disabled people']\n", + "dwarf 300375533 ['chick-pea (species)', 'chick pea (species)', 'chickpea (species)', 'garbanzo (species)', 'Bengal gram (species)', 'chestnut bean (species)', 'gram (species, chick-pea)', 'chich (species)', 'dwarf pea (species)', 'garavance (species)']\n", + "dwarf 300266100 ['dwarf lemurs and mouse lemurs']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300041590 ['dwarf tall clock', 'case clocks, dwarf tall', 'case clocks, miniature tall', 'clock, grandmother', 'clocks, dwarf tall', 'clocks, dwarf tall case', 'clocks, grandmother', \"clocks, grandmother's\", 'clocks, miniature tall case', 'dwarf tall case clocks', 'grandmother clocks', \"grandmother's clocks\", 'miniature tall case clocks', 'tall case clocks, dwarf', 'tall case clocks, miniature', 'tall clocks, dwarf']\n", + "dwarf 300386950 ['dwarf planet', 'planets, dwarf']\n", + "dwarf 300386950 ['dwarf planet', 'planets, dwarf']\n", + "dwarves 300236748 ['dwarf', \"dwarf's\", \"dwarfs'\", 'dwarves']\n", + "eskimo 300016731 ['Pre-Columbian Eastern Eskimo style', 'styles, Pre-Columbian Eastern Eskimo']\n", + "eskimo 300016731 ['Pre-Columbian Eastern Eskimo style', 'styles, Pre-Columbian Eastern Eskimo']\n", + "eskimo 300016736 ['Pre-Columbian Western Eskimo style', 'styles, Pre-Columbian Western Eskimo']\n", + "eskimo 300016736 ['Pre-Columbian Western Eskimo style', 'styles, Pre-Columbian Western Eskimo']\n", + "eskimo 300102550 ['Eskimo, Labrador', 'Inuit, Labrador', 'Labrador Eskimo', 'Labradormiut']\n", + "eskimo 300102550 ['Eskimo, Labrador', 'Inuit, Labrador', 'Labrador Eskimo', 'Labradormiut']\n", + "eskimo 300102489 ['Yupik (Eskimo)', 'Yupik (culture or style)', 'Alaskan Yupik', 'Yupik Eskimo', 'Asiatic Eskimo', 'Asian Eskimo']\n", + "eskimo 300102489 ['Yupik (Eskimo)', 'Yupik (culture or style)', 'Alaskan Yupik', 'Yupik Eskimo', 'Asiatic Eskimo', 'Asian Eskimo']\n", + "eskimo 300102489 ['Yupik (Eskimo)', 'Yupik (culture or style)', 'Alaskan Yupik', 'Yupik Eskimo', 'Asiatic Eskimo', 'Asian Eskimo']\n", + "eskimo 300102489 ['Yupik (Eskimo)', 'Yupik (culture or style)', 'Alaskan Yupik', 'Yupik Eskimo', 'Asiatic Eskimo', 'Asian Eskimo']\n", + "eskimo 300411929 ['Eskaleut', 'Eskimo-Aleut languages']\n", + "ethnic group 300191997 ['ethnic group', 'groups, ethnic']\n", + "ethnic group 300197770 ['ethnic group studies', 'studies, ethnic']\n", + "ethnic group 300250435 ['ethnic', 'ethnic group identity', 'ethnic identity']\n", + "gay 300400510 ['LGBT', 'lesbian, gay, bisexual, and transgender', 'lesbian, gay, bisexual, transgender/transsexual/transvestite', 'L.G.B.T.Q.', 'LGB', 'GLBT', 'LGBTQ']\n", + "gay 300400510 ['LGBT', 'lesbian, gay, bisexual, and transgender', 'lesbian, gay, bisexual, transgender/transsexual/transvestite', 'L.G.B.T.Q.', 'LGB', 'GLBT', 'LGBTQ']\n", + "gay 300391091 ['Gay-Lussac alcoholometer', 'alcoholometers, Gay-Lussac', \"Gay-Lussac's alcoholometer\"]\n", + "gay 300391091 ['Gay-Lussac alcoholometer', 'alcoholometers, Gay-Lussac', \"Gay-Lussac's alcoholometer\"]\n", + "gay 300391091 ['Gay-Lussac alcoholometer', 'alcoholometers, Gay-Lussac', \"Gay-Lussac's alcoholometer\"]\n", + "gay 300400507 ['male homosexual (sexuality)', 'gay (male homosexual)']\n", + "gay 300055188 ['homosexual (sexuality)', 'gay (general homosexuality)', 'queer (homosexual)']\n", + "gypsy 300199725 ['Dutch oven (cookware)', 'dutch oven (cookware)', 'ovens, Dutch (cookware)', 'bake kettle', 'bake kettles', 'bake oven (Dutch oven)', 'bake ovens (Dutch ovens)', 'dinner pot', 'dinner pots', 'Dutch pot (cookware)', 'Dutch pots (cookware)', 'gypsy pot', 'gypsy pots', 'stew pot', 'stew pots', 'oven, Dutch (cookware)']\n", + "gypsy 300199725 ['Dutch oven (cookware)', 'dutch oven (cookware)', 'ovens, Dutch (cookware)', 'bake kettle', 'bake kettles', 'bake oven (Dutch oven)', 'bake ovens (Dutch ovens)', 'dinner pot', 'dinner pots', 'Dutch pot (cookware)', 'Dutch pots (cookware)', 'gypsy pot', 'gypsy pots', 'stew pot', 'stew pots', 'oven, Dutch (cookware)']\n", + "gypsy 300404070 ['Roma (culture)', 'Gypsy', 'Gipsy']\n", + "gypsy 300195349 ['kettle (vessel)', 'gypsy kettles', 'kittles']\n", + "hermaphrodites 300233041 ['brigantine', 'brig-schooners', 'hermaphrodites (watercraft)']\n", + "homo 300265711 ['human (species)', 'humans (species)', 'man (Homo sapiens species)', 'human beings (species)']\n", + "homosexual 300400507 ['male homosexual (sexuality)', 'gay (male homosexual)']\n", + "homosexual 300400507 ['male homosexual (sexuality)', 'gay (male homosexual)']\n", + "homosexual 300055188 ['homosexual (sexuality)', 'gay (general homosexuality)', 'queer (homosexual)']\n", + "homosexual 300055188 ['homosexual (sexuality)', 'gay (general homosexuality)', 'queer (homosexual)']\n", + "homosexuals 300435114 ['male homosexual (person)', 'homosexuals, male']\n", + "immigrants 300025844 ['immigrant', \"immigrant's\", \"immigrants'\"]\n", + "indians 300017650 ['Indians (Sioux)', 'Dakota (culture or style)', 'Dakota Sioux', 'Siouan (culture or style)']\n", + "indigenous 300379660 ['indigenous person', 'indigenous peoples', 'aboriginal peoples', 'indigenous populations', 'native peoples', 'aborigines', 'indigenes', 'people, indigenous']\n", + "indigenous 300379660 ['indigenous person', 'indigenous peoples', 'aboriginal peoples', 'indigenous populations', 'native peoples', 'aborigines', 'indigenes', 'people, indigenous']\n", + "indigenous 300379660 ['indigenous person', 'indigenous peoples', 'aboriginal peoples', 'indigenous populations', 'native peoples', 'aborigines', 'indigenes', 'people, indigenous']\n", + "indigenous 300379660 ['indigenous person', 'indigenous peoples', 'aboriginal peoples', 'indigenous populations', 'native peoples', 'aborigines', 'indigenes', 'people, indigenous']\n", + "inuit 300102579 ['Greenlandic Inuit', 'Greenlandic Native']\n", + "inuit 300102550 ['Eskimo, Labrador', 'Inuit, Labrador', 'Labrador Eskimo', 'Labradormiut']\n", + "inuit 300265652 ['Ungava Inuit', 'New Québec Inuit', 'Quebec Inuit']\n", + "inuit 300265652 ['Ungava Inuit', 'New Québec Inuit', 'Quebec Inuit']\n", + "inuit 300265652 ['Ungava Inuit', 'New Québec Inuit', 'Quebec Inuit']\n", + "kaffir 300375528 ['sorghum (S. bicolor, species)', 'durra (species)', 'broomcorn (species)', 'broom-corn (species)', 'black amber (species)', 'grain sorghum (species)', 'Indian millet (species)', 'Sudan grass (species)', 'guinea corn (species)', 'wild cane (species)', 'shatter cane (species)', 'shattercane (species)', 'chicken corn (species)', 'sorghum guineense (species)', 'milo (S. bicolor, species)', 'kafir (species)', 'kaffir (species)', 'feterita (species)', 'kaoliang (species)', 'jowari (species)']\n", + "medicine men 300218522 ['shaman', \"shamans'\", \"shaman's\", 'medicine men', 'medicine women', 'men, medicine', 'women, medicine']\n", + "mestizo 300018103 ['Highland, Provincial', 'Mestizo']\n", + "mohammedan 300073715 ['Islamic (religion)', 'Islamism', 'Mohammedan', 'Mohammedanism', 'Moslem', 'Muhammadanism', 'Muslim', 'Muslimism', 'Mussulmanism', 'mahométanisme', 'islamisme']\n", + "moor 300375152 ['Maures', 'Moor (culture or style)', 'Mauri (Arab-Berber culture or style)']\n", + "negro 300018125 ['Afro-American', 'Black (African American)', 'Negro (African American)']\n", + "negro 300121558 ['Negro Renaissance', 'New Negro Movement', 'Renaissance, Harlem']\n", + "negro 300121558 ['Negro Renaissance', 'New Negro Movement', 'Renaissance, Harlem']\n", + "negro 300393224 ['Negro spiritual', 'spirituals', 'spirituals, Negro', 'African American spirituals', 'Afro-American spirituals']\n", + "negro 300393224 ['Negro spiritual', 'spirituals', 'spirituals, Negro', 'African American spirituals', 'Afro-American spirituals']\n", + "oriental 300375194 ['oriental plane (species)', 'oriental planetree (species)', 'chenar (species)', 'button-wood (Platanus orientalis)', 'buttonwood (Platanus orientalis)']\n", + "oriental 300375194 ['oriental plane (species)', 'oriental planetree (species)', 'chenar (species)', 'button-wood (Platanus orientalis)', 'buttonwood (Platanus orientalis)']\n", + "oriental 300374845 ['Japanese persimmon (species)', 'Asian persimmon (species)', 'Oriental persimmon (species)', 'kaki persimmon (species)', 'kaki (species)', 'shizi (species)']\n", + "oriental 300018279 ['Oriental (Asian)']\n", + "orientals 300185762 ['Oriental rug', 'oriental rug', 'carpets, Oriental', 'farash', 'ghali', 'hali (Oriental rugs)', 'Oriental carpets', 'Orientals (rugs)', 'qali (Oriental rugs)', 'rugs, Oriental']\n", + "pages 300055033 ['title page', 'title-pages', 'pages, title']\n", + "pages 300055033 ['title page', 'title-pages', 'pages, title']\n", + "primitive 300019021 ['Central Indian (miniature painting)', 'Primitive Rajasthani']\n", + "primitivism 300174254 ['Primitivism (Russian art movement)']\n", + "primitivism 300056548 ['neoprimitivism', 'neo-primitivism']\n", + "pygmy 300262937 ['Babenga', 'Babinga', 'Bambenga', 'Bebayaga', 'Bebayaka', 'Biaka', 'Bibaya', 'Binga', 'Mbaka (Pygmy)', 'Mbenga (Pygmy)']\n", + "pygmy 300262937 ['Babenga', 'Babinga', 'Bambenga', 'Bebayaga', 'Bebayaka', 'Biaka', 'Bibaya', 'Binga', 'Mbaka (Pygmy)', 'Mbenga (Pygmy)']\n", + "pygmy 300389910 ['pygmy (animal characteristic)']\n", + "pygmy 300100810 ['Batwa', 'Tswa (Pygmy)']\n", + "queer 300055188 ['homosexual (sexuality)', 'gay (general homosexuality)', 'queer (homosexual)']\n", + "race 300417371 ['multi-racial', 'racially mixed', 'mixed race', 'multirace']\n", + "races 300256475 ['races (groups of people)', 'peoples (races)']\n", + "races 300256475 ['races (groups of people)', 'peoples (races)']\n", + "retarded 300014934 ['class B gypsum plaster', 'gypsum plaster, class B', 'hemihydrate plaster, retarded', 'plaster, class B gypsum', 'plaster, retarded hemihydrate']\n", + "retarded 300014934 ['class B gypsum plaster', 'gypsum plaster, class B', 'hemihydrate plaster, retarded', 'plaster, class B gypsum', 'plaster, retarded hemihydrate']\n", + "servants 300136452 ['domestic (servant)', 'domestic servants', \"domestic's\", \"domestics'\"]\n", + "servants 300411753 [\"servant's uniforms\", \"servant's uniform\", 'servants dress']\n", + "servants 300113288 ['government employee', \"government employee's\", \"government employees'\", 'employees, government', 'civil servants', 'public employees', 'public servants']\n", + "servants 300113288 ['government employee', \"government employee's\", \"government employees'\", 'employees, government', 'civil servants', 'public employees', 'public servants']\n", + "slave 300419276 ['slave owner', 'slave-owner', 'slave master']\n", + "slave 300419276 ['slave owner', 'slave-owner', 'slave master']\n", + "slave 300419276 ['slave owner', 'slave-owner', 'slave master']\n", + "third world 300379994 ['developing country', 'Third World', 'emerging nations', 'developing nations', 'least-developed countries', 'less-developed countries', 'LDCs', 'countries, developing']\n", + "traditional 300435679 ['traditional cultural property', 'traditional cultural places', 'TCP']\n", + "traditional 300435679 ['traditional cultural property', 'traditional cultural places', 'TCP']\n", + "trans 300417823 ['transatlantic imprint', 'imprints, transatlantic', 'trans-atlantic imprints']\n", + "trans 300022218 ['Transavanguardia', 'Transavantgarde', 'trans-avant-garde']\n", + "trans 300411958 ['Trans-New Guinea languages (language family)']\n", + "transvestite 300400510 ['LGBT', 'lesbian, gay, bisexual, and transgender', 'lesbian, gay, bisexual, transgender/transsexual/transvestite', 'L.G.B.T.Q.', 'LGB', 'GLBT', 'LGBTQ']\n" + ] + } + ], + "source": [ + "# altLabels no markers\n", + "case_2 = []\n", + "case_2_count = 0\n", + "for term, hits in aat_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"altLabel\":\n", + " if hit[\"aat_uri\"] not in e_aat_implicit and hit[\"aat_uri\"] not in e_aat_explicit:\n", + " case_2_count += 1\n", + " case_2.append(hit[\"aat_uri\"])\n", + " print(term, hit[\"aat_uri\"], hit[\"altLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "128" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_2_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/aat_{lang}_case2.txt\",'w') as txt_file:\n", + " for l in case_2:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "disabled 300025925 ['developmentally disabled', 'mentally retarded']\n", + "dwarf 300310411 ['bonobo (species)', 'bonobos (species)', 'pygmy chimpanzees (species)', 'pygmy chimps (species)', 'dwarf chimpanzees (species)', 'gracile chimpanzee (species)']\n", + "eskimo 300017455 ['Canadian Eskimo', 'Eskimo, Canadian']\n", + "eskimo 300017455 ['Canadian Eskimo', 'Eskimo, Canadian']\n", + "eskimo 300017447 ['Eskimo Tradition']\n", + "first world 300449024 ['developed country', 'developed world', 'First World']\n", + "indian 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "indian 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "indian 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "indo 300386794 ['Aryan (Indo-European culture)', 'Arian (Indo-European culture)', 'Indo-Germanic', 'Japhetic']\n", + "indo 300386794 ['Aryan (Indo-European culture)', 'Arian (Indo-European culture)', 'Indo-Germanic', 'Japhetic']\n", + "indo 300386794 ['Aryan (Indo-European culture)', 'Arian (Indo-European culture)', 'Indo-Germanic', 'Japhetic']\n", + "maroon 300443390 ['maroon']\n", + "native 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "native 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "native 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "native 300017437 ['American Indian', 'Indigenous American', 'Indian (Native American)', 'Native (Native American)', 'American, Native', 'Indian, American', 'Native Americans']\n", + "primitive 300056460 ['architecture, primitive']\n", + "primitive 300056500 ['art, primitive']\n", + "pygmy 300310411 ['bonobo (species)', 'bonobos (species)', 'pygmy chimpanzees (species)', 'pygmy chimps (species)', 'dwarf chimpanzees (species)', 'gracile chimpanzee (species)']\n", + "pygmy 300310411 ['bonobo (species)', 'bonobos (species)', 'pygmy chimpanzees (species)', 'pygmy chimps (species)', 'dwarf chimpanzees (species)', 'gracile chimpanzee (species)']\n", + "pygmy 300016430 ['Pigmy (African culture or style)', 'Bakola (Pygmy, culture or style)']\n", + "retarded 300025925 ['developmentally disabled', 'mentally retarded']\n", + "servants 300025874 ['servant', \"servant's\", \"servants'\"]\n", + "slave 300055309 ['slave keeping']\n", + "slaves 300230899 ['enslaved person', 'enslaved persons', 'slaves (people)', 'slave (person)', \"slave's (person's )\", \"slaves' (peoples')\", 'people, enslaved']\n", + "slaves 300230899 ['enslaved person', 'enslaved persons', 'slaves (people)', 'slave (person)', \"slave's (person's )\", \"slaves' (peoples')\", 'people, enslaved']\n" + ] + } + ], + "source": [ + "# altLabels with markers\n", + "case_2_markers = []\n", + "case_2_markers_count = 0\n", + "for term, hits in aat_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"altLabel\":\n", + " # either markers\n", + " if hit[\"aat_uri\"] in e_aat_implicit or hit[\"aat_uri\"] in e_aat_explicit:\n", + " case_2_markers_count += 1\n", + " case_2_markers.append(hit[\"aat_uri\"])\n", + " print(term, hit[\"aat_uri\"], hit[\"altLabel\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "27" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_2_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/aat_{lang}_case2_with_markers.txt\",'w') as txt_file:\n", + " for l in case_2_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 3" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal 300120040 Describes the style and culture of the Aboriginal Australian group located in Arnhem Land, a northeastern territory in Australia. The Fijian missionaries introduced fan making to the original inhabitants of Arnhem Land.\n", + "aboriginal 300435249 General designation for the race, ethnicity, styles, culture, and heritage of people of sub-Saharan African origin or descent in places outside Africa, or of members of any dark-skinned group of peoples, including those of Australian Aboriginal origin or descent.\n", + "aboriginal 300435341 Culture and ethnicity of the aboriginal people inhabiting the forest districts of Sri Lanka prior to the 6th century BCE. They adopted Sinhala and now no longer speak their own language. Ethnically, they are allied to the indigenous jungle peoples of southern India and to early populations in Southeast Asia.\n", + "aboriginal 300198715 In general, the term usually refers to a culture or style produced by people who were born in the Americas or nearby islands, but who were descended from colonists or slaves, as distinguished from people who arrived directly from Europe or Africa, or who were descended from aboriginal populations. It is used to refer to the cultures of different populations in the context of different regions; its usage is often contradictory from region to region. It refers to the culture and styles produced by white people who had Spanish parents and were born in the Spanish territories of North and South America in the sixteenth through eighteenth centuries; their culture and social position were distinguished from residents who had been born in Spain. In modern usage in the context of Latin America, it may refer to the culture of people born locally but of pure Spanish extraction or specifically to traditions of old-line families of predominantly Spanish descent. The term may also refer to the culture of early South American blacks born in America, as distinguished from blacks brought directly from Africa. In Louisiana in the United States it refers to the culture of either French-speaking white descendants of early French and Spanish settlers or of mulattos speaking a form of French and Spanish patois. It may also refer to the culture of people in the West Indies who were born and naturalized there, but were of Spanish, French, or African descent; in modern usage in the context of the Caribbean, it is often used to refer to Caribbean culture in general, including elements from European, African, Asian, and Amerindian sources.\n", + "aboriginal 300387326 Tracts of land set aside by a government for aboriginal, tribal, or native populations.\n", + "aboriginal 300264789 South Australian carved sculptures made of wood, gypsum, and ochre, which function as direction-markers. These sculptures were placed in the ground to indicate which particular tribal group inhabited the site or in which direction they could be found. The aboriginal Australians named Diyari constructed these innovative signposts at the Lutheran Mission at Killalpaninna between 1903 and 1906. Toas are not a traditional form of sculpture; it is believed that the production of toas was by the request of Europeans interested in aboriginal culture. Toas were only produced in the South Australian state.\n", + "aboriginal 300386485 Style and culture of one of the largest Indian scheduled tribes, an aboriginal people of the Choṭa Nāgpur region in the state of Bihār, India. They call themselves Kurukh; they once lived farther to the southwest on the Rohtās Plateau, but they were dislodged by other populations and migrated to Choṭa Nāgpur, where they settled in the vicinity of Munda-speaking tribes.\n", + "aboriginals 300438772 Cultures and styles of the Amis people lived in Taiwan. The Amis people refer to themselves in two ways: Pangcah meaning “we people” is used in regions north of Taitung, and Amis meaning “northerners” is used in the south. The denomination has to do with routes of migration and interaction among tribes. The Chinese term came to adapt Amis. The Amis territory stretches from the Qilai plain to the Hengchun peninsula, where the Amis people develop an agrarian culture intricately rooted in the low lands of Taiwan’s eastern valley and coastal plains. The Amis has the largest population of aboriginals in Taiwan.There are three subcategories of the Amis people based on geographical and cultural-linguistic differences: The Northern group of “Nanshi” Amis, the Middle group of “Xiuguluan” Amis and coastal Amis, and the Southern group of “Falangaw” Amis and Hengchun Amis.The property inheritance of the Amis is matrilineal and traditional matrimony follows the rule of mikadafo which marries Amis men into the brides’ homes. The Amis tribe is co-governed by clan chiefs, who assign responsibilities and tasks to male members of different age classes. The Harvest Festival, known as Malalikid, is the most important celebration which unifies traditional beliefs, social structure and tribal identity.\n", + "barbarian 300018409 Refers to the Chinese dynastic culture, style, and period dating 386 to 534 CE. Its capital was initially at Pingcheng but was moved south to Luoyang in 493-494 by Emperor Xiaowendi (reigned 471-499) where a new magnificent city was built on the ruins of the old Chinese capital; by 534 the population was more than half a million. Buddhist art flourished under state and private patronage during most of this period. Cave temples at Yungang were begun in ca. 460; thousands of craftsmen worked for about 35 years to make the temples and adorn them with sculpture and painting. Other cave temples were later made at Longmen at the instigation of Xiaowendi. While Yungang features static icons in a Gandharan style, the sculpture at Longmen is more linear, demonstrating the emerging Chinese style. Northern Wei burial pottery, also influenced by Buddhism, emphasizes frontality and symmetry. The nomadic Touba people began to rely on Chinese institutions to organize and run their state and they also became accustomed to Chinese culture and luxuries; under Xiaowendi Chinese became the official language and the use of Tuoba language was forbidden. The distinction between the 'barbarian' north and 'civilized' south became less marked; nevertheless, northern frontiersmen began to feel neglected and so they revolted, leading to the collapse of the Northern Wei dynasty. Northern China was divided into the Eastern and Western Wei dynasties in 534.\n", + "batavia 300012925 General term referring to various dammar resins that were formerly shipped under the tradename \"Batavia\" from Jakarta (formerly Batavia), Indonesia. General term referring to various dammar resins that were formerly shipped under the tradename \"Batavia\" from Jakarta (formerly Batavia), Indonesia.\n", + "berber 300263397 Style and culture of the African people who are a subgroup of the Berber, living in Awjilah, Cyranainca, northeast Libya.\n", + "berber 300263728 Style and culture of the Berber people of the same name living in the coastal area west of Algiers, Algeria.\n", + "berber 300263735 Style and culture of the Berber people of the same name living in the African region of Mauritania.\n", + "berber 300263737 Style and culture of the Berber people livng in settled areas of southern Tunisia.\n", + "berber 300263738 Style and culture of the Berber people of the same name living primarily in the Algerian Saharan towns of Ghardaia, Gurara, and Berriane.\n", + "berber 300263998 Describes works created by the African people of the same name, a nomadic Berber group living in Mauritania and Mali.\n", + "berber 300263740 Style and culture of the Berber people of the same name living in northwestern Algeria.\n", + "berber 300263729 Style and culture of the Berber people of the same name living in the High Atlas and Anti Atlas mountains as well as the Dra and Sous regions of Morocco, and in western Algeria.\n", + "berber 300016595 Style and culture of the Berber people of the same name, living in the Sahara and North Africa.\n", + "berber 300375152 Style and culture of a people of mixed Arab-Berber descent inhabiting the Western Sahara, neighboring parts of Morocco, Mali, Algeria, and the Islamic Republic of Mauritania. To refer to the products, style and culture of people living within the boundaries of Mauritania proper use \"Mauritanian.\"\n", + "black 300262593 Carved wooden masks of the Songye people of the Democratic Republic of Congo in Africa, existing in both \"female\" and \"male\" types; the female type is used in burial rituals and the consecration of new chiefs, while the male type is used to impose discipline among the ranks of the circumcised. In form they are distinguished by prominent facial features, often including a crest, and stripes of black, red, and white. They embody attributes of the human, the animal, and the spirit.\n", + "black 300448122 Originally, make-up or costume intended to imitate the appearance of a black person, particularly as part of a performance. By extension, any practice of stereotyping dark-skinned people in an exaggerated fashion. Though not exclusive to the United States, blackface was associated with minstrel shows in the US from the 1830s until the mid-20th century; and is widely regarded now as an offensive example of racism. Blackface was adopted by some African American performers in minstrel shows from ca.1840 as a means to earn a living in venues that were otherwise denied them in mainstream show business.\n", + "black 300449148 Culture and styles of British citizens or residents of either African or African-Caribbean origin or descent. Black British is one of various self-designation entries used in official UK ethnicity classifications.\n", + "black 300020118 Refers to the culture and styles that developed in Athens or elsewhere in Attica, particularly to painted pottery styles that developed chronologically after the Geometric styles. Attic styles are intentionally different from Corinthian styles, and are characterized by imaginative compositions that do not necessarily comply with standards of scale or balance, by monumentality and grandeur, and eventually by a distinctive Black-figure style that became the standard for the rest of the Greek world.\n", + "black 300021925 Describes the style and culture of the inhabitants of Buka Island. Changes in late 20th-century Buka art have their origins in the encounter between Pacific Islanders and the outside world. Whale hunters of the 1800s found the Buka paddles ideally suited to their work; as a result promoting the production of paddles by the Buka people. Lapita pottery and related materials have varied in style into the late 20th century. The people of Buka are known to represent human and animal forms in a naturalistic fashion, however human heads are also constructed in a canine-like style with the jaw protruded outward. Surfaces are often stained black and enhanced with inlaid patterns of red and white pigments. \n", + "black 300019470 Refers to the culture and styles associated with the Celts, an early Indo-European people who spread over Europe, from the British Isles and northern Spain to east of Transylvania, the Black Sea coasts, and Galatia in Anatolia, from the second millennium BCE to the first century BCE. Elements of the style persisted for centuries in southern Scandinavia and the post-Roman British Isles. It is characterized by a reference to the art of ancient Italy, Greece, and the East, combined in a new and individual style that includes a strong sense of form and structure, stylized plant, animal, and human forms, a balance of voids and ornament, vigorous vitality, and contrasts of texture.\n", + "black 300443479 A term used to describe that portion of all people, primarily in the United States, but perhaps used more widely, who are black, that is, dark-skinned peoples of Africa, Oceania, and Australia or their descendants, without regard to perceived actual skin tone. Indigenous refers to people of ethnic groups native to the Americas. People of color being a broad term for any non-Anglo-Saxon people.The term BIPOC is meant to be inclusive of those who are affected by racism, discrimination, or oppression based on ethnicity or race-based tropes.\n", + "black 300400853 Complex of beliefs concerning the gods and the nature of the cosmos developed by the Germanic-speaking peoples before their conversion to Christianity. Germanic culture extended, at various times, from the Black Sea to Greenland, or even the North American continent. Germanic religion played an important role in shaping the civilization of Europe.\n", + "blacks 300198715 In general, the term usually refers to a culture or style produced by people who were born in the Americas or nearby islands, but who were descended from colonists or slaves, as distinguished from people who arrived directly from Europe or Africa, or who were descended from aboriginal populations. It is used to refer to the cultures of different populations in the context of different regions; its usage is often contradictory from region to region. It refers to the culture and styles produced by white people who had Spanish parents and were born in the Spanish territories of North and South America in the sixteenth through eighteenth centuries; their culture and social position were distinguished from residents who had been born in Spain. In modern usage in the context of Latin America, it may refer to the culture of people born locally but of pure Spanish extraction or specifically to traditions of old-line families of predominantly Spanish descent. The term may also refer to the culture of early South American blacks born in America, as distinguished from blacks brought directly from Africa. In Louisiana in the United States it refers to the culture of either French-speaking white descendants of early French and Spanish settlers or of mulattos speaking a form of French and Spanish patois. It may also refer to the culture of people in the West Indies who were born and naturalized there, but were of Spanish, French, or African descent; in modern usage in the context of the Caribbean, it is often used to refer to Caribbean culture in general, including elements from European, African, Asian, and Amerindian sources.\n", + "bombay 300264498 Refers to modern-day Zoroastrian high priests. Dasturs oversee the liturgical lives of the important fire temples with which they are associated, assisted by a team of mobeds. This rank of priest is akin to that of the bishop in Christianity. The dasturs have a strong tradition of learning, especially among the Parsis in Bombay.\n", + "bombay 300264320 Refers to a Hindu sect and reform movement founded by the brahman Dayananda Sarasvati in Bombay in 1875. Followers, striving for a return to the original purity of Hinduism found in the Vedas, are against image-worship, child-marriage, polygamy and meaningless ritual. Dayananda's book 'Vedabhashya' contains his interpretations of the Vedas, the earliest Hindu scriptures. Arya Samaj promotes a moral vision of kindness and goodwill to all. Arya Samaj, now a worldwide organization, is also opposed to the traditional Hindu caste system and works to remove religious and social injustices. Arya Samaj followers also introduced the novel idea of converting to Hinduism people of other faiths. In 1893 there was a split between conservative and liberal followers who disagreed on whether to advocate traditional or modern forms of education and on whether to advocate vegetarianism or freedom of diet. The movement became nationalistic and was in conflict with Sikhs and Muslims, especially in the Punjab around the time of the partition of India and Pakistan in 1947.\n", + "bombay 300417414 A style of painting in India from the mid 19th to the beginning of the 20th century that emphasises Western techniques of realism under the influence of art academies established by the British Raj in key colonial cities such as Bombay and Calcutta. Due to increased patronage of art by the Indian elite and the rise of salon exhibitions, realistic oil painting was in high demand, especially portraiture and historical subjects, and remained popular until the development of the Bengal School. \n", + "bombay 300228512 Tenement houses characteristic of Bombay and other industrial Indian cities; originally developed in the late 19th century to house migrant industrial workers.\n", + "burma 300375367 Genus containing three species of tropical hardwood trees native to south and southeast Asia, particularly India, Pakistan, Bangladesh, Burma, Indonesia, and Thailand; commonly a component of monsoon forest vegetation.\n", + "burma 300375431 Species of large tree indigenous to eastern Asia, Myanmar (Burma), and Assam state of India. It appears to have been domesticated about 2,000 BCE in India, then brought to East Asia in the 5th century BCE. It produces a sweet orange-colored drupe fruit, one of the most important and widely cultivated fruits of the tropical world. The fruit varies greatly depending upon the variety, from those the size of plums to others weighing 4 to 5 pounds. \n", + "burma 300022012 The form of Buddhism practiced in the South Asian countries of Sri Lanka, Burma, Cambodia, Thailand, and Laos. Its doctrine, relatively unchanged since the 3rd century BCE, is based on the 'tipitaka' or Pali Canon and consists of a conservative interpretation of the Buddha's teachings. Theravada's main distinction from later Mahayana is its rejection of bodhisattvas. While the ultimate goal of Theravada is to become a 'perfected saint' or 'arhat,' lay believers cannot attain true enlightenment. True enlightenment is only reached by entering religious orders and even then it is nearly impossible for anyone to become a Buddha.\n", + "burma 300410257 Culture of the tribal Tibeto-Burman ethnic group inhabiting parts of northeastern Myanmar (Burma) and contiguous areas of India (Arunachal Pradesh and Nagaland) and China (Yunnan).\n", + "burma 300107052 Refers to one of many ethnic cultures of modern Myanmar. It also identifies the last capital of the Burmese empire built in 1857-1859 on the Irrawaddy River by King Mindon before the fall of Burma to British imperialists in 1885. Architectural art in this region reflects Italian influences as depicted in composite temple and monastery structures comprised of stone and native wood.\n", + "burma 300019089 Nationality, culture, and style of the Mon people of Indo-Chinese origin, now inhabiting eastern Burma (Myanmar) and western Thailand but having their ancient capital at Pegu in southern Burma. They represent a former empire that flourished from the 9th to the 11th and from the 13th to the 16th centuries. The culture has dominated the region for the last 1,200 years, replacing Sanskrit with Pali writing and introducing Theravada Buddhism to the ancient Burmese culture. Art of this region has shared historical ties with the ancient Cambodian kingdom of Funan, and with China, and was heavily influenced by the Angkor civilization.\n", + "burma 300410258 Culture of the tribal hill people of the Shan region and adjacent areas of eastern Myanmar (Burma), as well as southwestern Yunnan province of China. Some Palaung groups are organized in patrilineal lineages similar to those of the Kachin, their neighbours to the north; elsewhere their organization is more like that of the Shan. Shan-type Buddhism coexists with various local cults based on ancestor worship. \n", + "burma 300410260 Culture of the Southeast Asian people who live primarily in eastern and northwestern Myanmar (Burma) and also in Yunnan province, China. The Shan are the largest minority group in Myanmar. The Shan are Theravada Buddhists and have their own written language and literature. Most live on the Shan Plateau, which is seamed by low mountains and masses of broken, forested hills.\n", + "burma 300386148 Nationality and culture of the region between India and China, the areas of the current nations Burma, Kampuchea (Cambodia), Laos, Thailand, Vietnam and Malaysia.\n", + "burma 300266481 Styles and cultures existing in the extensive area that includes the nations of southwest Asia and northeastern Africa. The term was formerly used to also include Afghanistan, Pakistan, India, and Burma.\n", + "calcutta 300018988 A style of watercolor painting used by artists working in Calcutta, India in the nineteenth century; the works produced were sold inexpensively to pilgrims to the nearby Kalighat temple. This style demonstrates the European influence on Indian folk art; not only was the English technique of transparent watercolor adopted, but European subjects and events were sometimes depicted. Overall, these rapidly produced paintings are characterized by bold colors, broad sweeping brush lines, simplified forms, and little or no backgrounds. Popular Hindu deities are most commonly depicted although scenes of contemporary life are found as well. The style, which arose to compete with inexpensive colored lithographs, soon lost the contest. Although it quickly disappeared, the Kalighat style was influential for a number of modern Indian painters.\n", + "calcutta 300417414 A style of painting in India from the mid 19th to the beginning of the 20th century that emphasises Western techniques of realism under the influence of art academies established by the British Raj in key colonial cities such as Bombay and Calcutta. Due to increased patronage of art by the Indian elite and the rise of salon exhibitions, realistic oil painting was in high demand, especially portraiture and historical subjects, and remained popular until the development of the Bengal School. \n", + "caucasian 300391253 Composite mixture of pigment having a pinkish hue, often available pre-mixed, and intended for use as a flesh color resembling Caucasian flesh tones. Typically used only in western art prior to the early 1900s. Types and proportions of the pigments used for this mixture varied. For the technique of painting to resemble flesh tones, particularly Caucasian, use \"encarnacione (technique).\"\n", + "caucasian 300244538 Textile styles belonging to Central Caucasian cultures.\n", + "caucasian 300244674 Style of handwoven floor coverings made in the vicinity of Baku, Azerbaijan, a major port on the Caspian Sea. Rugs have been woven in this area since at least the 18th century and probably long before, although it is difficult to determine which were woven in the city and which in such nearby villages as Surahani and Chaildag. The so-called Chila rugs were almost certainly woven in this area. The earliest examples are larger than most Caucasian rugs, ranging up to 12 feet in length (3.6 metres). Most of these rugs have a blue field, and characterized by either an avshan (scattered floral sprig) or harshang (crab) design. Examples from later production may have some cotton in the wefts and are more likely to show a boteh (pear-shaped motif) design, often with a small medallion.\n", + "caucasian 300244539 Textile styles belonging to East Caucasian cultures.\n", + "caucasian 300182578 Technique involving the working of the surface of certain areas of a painting or polychromed carved figure to imitate the color and shading of human flesh; usually referring to Caucasian flesh color. The term was first coined in reference to Spanish art, but may be applied to any western art; particularly in use prior to the early 1900s. In some cases, certain artists specialized in encarnacione, while other artists would paint drapery, landscape, and other areas of the work.\n", + "caucasian 300244540 Textile styles belonging to South Caucasian cultures.\n", + "caucasian 300244687 Caucasus floor coverings woven in the vicinity of Quba in northern Azerbaijan, with major varieties woven near the towns of Perepedil, Divichi, Konaghend, Zejwa, Karagashli, and Kusary. They are as a group the most finely knotted Caucasian rugs. The Perepedil shows a highly geometrized floral design on a blue or ivory field. The Konaghend most frequently features a large central medallion. The Karagashli usually contains isolated elements from the Persian avshan \"sprig\" or harshang \"crab\" designs. The most common type of large, red-field Caucasian soumak rug was woven in the nearby town of Kusary.\n", + "caucasian 300244158 Style of textiles, particularly carpets, from the area around Karaja and the nearby range of Karadagh mountains in northwestern Iran, just south of the Azerbaijan border northeast of Tabriz. The carpets are thick, woollen and knotted with either a geometrical or a floral pattern. The best-known pattern shows three geometric medallions that are similar to those in Caucasian carpets; the central medallion has a latch-hooked contour and differs in color from the others, which are eight-pointed stars.\n", + "colored 300310660 General term referring to around 18 species in different genera of parrots, having in common that they are large, colorful, native to tropical America, have a very large beak that is dark in color, and have a relatively featherless, light colored, facial patch.\n", + "colored 300013583 Generic name for red-colored substances of similar composition obtained from the roots of either of two species of plants. In the near East and Europe, alkanet is extracted from Anchusa officinalis. In Asia, alkanet is extracted from Lawsonia inermis. The primary colorant is alkanninH. It was used in late Egyptian times through the Middle Ages as a red dye; use as dye was discontinued because of poor lightfastness. The compound has been used as a textile dye, wood stain, lake pigment, cosmetic, as an acid-base indicator, and for medicinal purposes.\n", + "colored 300264634 Refers to a variety of agate containing brown or black moss- or tree-like dendritic forms. It is typically a grayish to milky-white agate, which is a variety of the silica mineral quartz. It contains opaque, dark-colored inclusions with feathery, branching forms that resemble ferns, moss, or other vegetation but that are in fact of inorganic origin, mainly manganese and iron oxides. Most examples of moss agate are found as fragments of weathered from volcanic rocks from India, Brazil, Uruguay, central Europe, and the western United States. The stone has historically been used for ornamental purposes, often cut in flat or rounded forms, and sometimes dyed to improve its color. \n", + "colored 300011161 A high grade of massive talc occurring in the Appalachian region in the United States that can be cut to shape and used for marking purposes; it is usually white in color but may be colored gray or yellow by impurities.\n", + "colored 300266080 The effect of graduated or shaded color in textiles, created through the weave or by dyeing. The effect may be monochromatic or polychromatic. The term is most often used for textiles, but may also be extended to painted or colored surfaces that display a graduated shading effect.\n", + "colored 300012482 Wood of the species Juglans regia, native to the Himalayas, Iran, Lebanon, Asia Minor, and Greece. It was introduced into Britain in the mid-15th century. It has a uniform, deep brown color with a medium texture and a close, straight grain. It varies considerably in color the sapwood being pale straw with grayish-brown heartwood with infiltrations of coloring producing a darker-colored streaky appearance. It is strong but easy to work and polishes to a high gloss. It is used for furniture, veneers, cabinets, paneling, gun stocks. Its burls are especially prized in the furniture trade. For the darker wood from the species Junglans nigra found in the eastern United States, use \"black walnut.\"\n", + "colored 300013423 Pigments of various compositions, having in common that they are all made from green colored siliceous, iron-rich clays that have been used as pigments since ancient times, ground from available minerals, including celadonite, glauconite, cronstedtite, montmorillonite, and chlorite, among others. The color of green earth pigment can range from yellow-green to sea-green to greenish-gray, is translucent in oils, having moderate tinting strength and poor hiding power. It is a permanent, stable pigment that is compatible with all media. Green earth is sometimes imitated by mixtures of Naples yellow and Prussian blue.\n", + "colored 300012939 Translucent golden-colored resin composed of a yellow resinous component and a clear water-soluble gum, produced by several trees of the genus Garcinia native to India, Thailand, Cambodia, Vietnam, and Sri Lanka. Gamboge was used as a yellow pigment as early as the 8th century in Asia and Japan. It was regularly imported to Europe in the 17th century. It is marketed in the form of dull, brownish-yellow cakes or lumps that, when powdered, have a rich golden color. The carbohydrate gum acts as a natural binder. Gamboge is used as a transparent colorant in glazes, varnishes, and watercolors. The yellow color fades when exposed to light or ozone. In some cases it has recovered its color when placed in the dark.\n", + "colored 300379604 Trademarked general term for daylight fluorescent and glow-in-the-dark paints and pigments, including objects colored by the pigments. Originally used only for products manufactured by Day-Glo Color Corporation, Cleveland, although the term is commonly used generally for flourescent pigments.\n", + "colored 300263717 Refers to a type of glass that is characterized by an irregular rippled effect in the color, caused by a mixture of glass of different hardnesses. It is usually a blend of white with colored glass, the word \"reamy\" referring to the creamy white color. It may be similar in appearance to \"cloudy glass\" and \"streaky glass.\" It is often used to make windows.\n", + "descent 300264336 Refers to the descent to earth of a Hindu deity in a visible form. The word comes from the Sanskrit meaning 'descent.' The concept comes from the tradition associated with the deity Vishnu who periodically appeared on earth in human or animal form in order to save it from severe danger or destruction. Vishnu's most famous manifestations have been as Krishna and Rama. The deity is expected to return in the last of his forms to destroy and subsequently recreate the world at a time when it is completely depraved. In more recent times the concept has been challenged by reformers, particularly in regards to manifestations in animal forms. At the same time, others have put forward the idea that humans, even non-Hindus such as Jesus or Muhammad, can become avataras by a divine infilling.\n", + "descent 300255718 Those from whom a person is descended, usually considered to be those more remote in the line of descent than grandparents.\n", + "descent 300449148 Culture and styles of British citizens or residents of either African or African-Caribbean origin or descent. Black British is one of various self-designation entries used in official UK ethnicity classifications.\n", + "descent 300411617 The right to own a particular property, where that ownership is regularly evidenced and capable of recognition and enforcement in a court of law. The law typically considers the legal title as resting in the last party to whom it was transmitted by descent or by purchase through a regularly connected chain of transmission from the original source of title.\n", + "descent 300016575 Refers to the people and culture of southern Africa whom the first European explorers found in areas of the hinterland and who now live either in European settlements or on official reserves in South Africa or Namibia. Most Khoikhoi are either Nama or Oorlams, the latter term denoting remnants of the \"Cape Hottentots\" together with many of hybrid descent. The main Nama concentrations are the Bondelswarts, Rooinasie, Swartboois, and Topnaars; the main Orlams groups are the Witbooi, Amraal, Berseba, and Bethanie. The Khoikhoi are not easily distinguishable physically from the San, the Khoikhoi's slightly taller stature and decidedly longer and narrower head being the only marked differences.\n", + "descent 300027015 Accounts or histories of the descent of persons, families, or other groups, from an ancestor or ancestors; enumerations of ancestors and their descendants in the natural order of succession.\n", + "descent 300198715 In general, the term usually refers to a culture or style produced by people who were born in the Americas or nearby islands, but who were descended from colonists or slaves, as distinguished from people who arrived directly from Europe or Africa, or who were descended from aboriginal populations. It is used to refer to the cultures of different populations in the context of different regions; its usage is often contradictory from region to region. It refers to the culture and styles produced by white people who had Spanish parents and were born in the Spanish territories of North and South America in the sixteenth through eighteenth centuries; their culture and social position were distinguished from residents who had been born in Spain. In modern usage in the context of Latin America, it may refer to the culture of people born locally but of pure Spanish extraction or specifically to traditions of old-line families of predominantly Spanish descent. The term may also refer to the culture of early South American blacks born in America, as distinguished from blacks brought directly from Africa. In Louisiana in the United States it refers to the culture of either French-speaking white descendants of early French and Spanish settlers or of mulattos speaking a form of French and Spanish patois. It may also refer to the culture of people in the West Indies who were born and naturalized there, but were of Spanish, French, or African descent; in modern usage in the context of the Caribbean, it is often used to refer to Caribbean culture in general, including elements from European, African, Asian, and Amerindian sources.\n", + "descent 300386015 Broad designation encompassing cultures of all European peoples who speak languages descended from Latin; originally with the erroneous implication that these peoples are of Roman descent.\n", + "descent 300264324 A Christian renewal movement that emphasizes the descent of the Holy Spirit on the apostles at the first Christian Pentecost. The modern Pentecostal movement arose in the United States in 1901 with Charles Parham who linked baptism with speaking in tongues. The reappearance of prophecy and healing are also part of Pentacostalism. Pentecostal churches are characterized by their various forms of participatory and informal worship and by their literal interpretation of the Bible. The movement probably appeals to impoverished and less-educated people in part because there is a general emphasis on spiritual experience rather than intellectual reflection. Missionary work is typically a high priority but the formation of a representative body of Pentecostals is usually opposed just as is the ecumenical movement. Since the 1960s Pentacostalism has appeared within the Roman Catholic, Protestant, and Greek Orthodox churches.\n", + "descent 300375152 Style and culture of a people of mixed Arab-Berber descent inhabiting the Western Sahara, neighboring parts of Morocco, Mali, Algeria, and the Islamic Republic of Mauritania. To refer to the products, style and culture of people living within the boundaries of Mauritania proper use \"Mauritanian.\"\n", + "disabled 300189309 Condition manifested by subnormal intellectual functioning that originates during the developmental period. This has multiple potential etiologies, including genetic defects and perinatal insults. Intelligence quotient (IQ) scores are commonly used to determine whether an individual has an intellectual disability. IQ scores between 70 and 79 are in the borderline range; scores below 67 are in the disabled range.\n", + "disabled 300006719 Facilities providing basic living assistance and health care for disabled or elderly retired persons, especially such facilities in socialist and communist countries.\n", + "disabled 300343487 Locally administered public or private institutions for care of the homeless, disabled, and elderly without means; often operated in conjunction with a farm, with emphasis on meeting operating costs through the sale of farm produce. Almshouses incurred widespread criticism after the turn of the 20th century for failure to provide differentiated treatment for the varying problems presented by residents. For earlier institutions where the disabled, elderly poor, or vagrants were confined for reform and work, use \"workhouses (institutions).\" For institutions established solely for the distribution of alms, use \"almonries (institutions).\" Buildings where the indigent or otherwise helpless without further recourse are cared for and put to work at public expense; in the United States, established since the mid-18th century and usually funded by local or state governments or parishes; in England, originally under the administration of monasteries for dispensing alms, later endowed by private charities. For buildings where the disabled, elderly poor, or vagrants are confined for reformative and correctional purposes, use \"workhouses.\" For places established solely for the distribution of alms, use \"almonries.\"\n", + "disabled 300006745 Buildings housing locally administered public or private institutions for care of the homeless, disabled, and elderly without means; often operated in conjunction with a farm. For earlier buildings where the disabled, elderly poor, or vagrants were confined for reform and work, use \"workhouses (buildings).\" For places established solely for the distribution of alms, use \"almonries (buildings).\"\n", + "disabled 300000311 Housing constructed or altered to facilitate the particular needs of the disabled, particularly the physically disabled, for example including wheelchair ramps rather than or in addition to stairways.\n", + "disabled 300386051 Frameworks used to assist mobility for the disabled or infirm, or designed to support babies learning to walk. \n", + "discover 300391311 Nondestructive evaluation technique similar to electron speckle pattern interferometry (ESPI) used to discover cracks, deformations, and other flaws in materials. It employs coherent laser light to create an interference pattern, or speckle, on the surface it illuminates. Shearography uses the test object itself as reference, creating a sheared, or double image, which superimposes the object with speckle pattern on the sample with reference light.\n", + "discover 300264523 Devices comprising sticks or rods; used by people working above ground in an attempt to discover water, minerals, treasure, archaeological remains, graves, or other things below ground. Use of rods for these purposes has ancient origins; devices similar to those used today are first documented in 16th-century Europe. Traditionally Y-shaped twigs, often of hazel, rown, or willow which, when their two prongs are grasped, twist and dip in the hands of the dowser as he or she approaches the substances or objects sought for. Alternatively, the rods consist of two metal rods held parallel a few inches apart, that swing across each other when nearing the sought-after substance or objects. In controlled studies, the success rate of finding anything below ground by using these devices is no better than chance.\n", + "discover 300137801 Testing a hypothesis or model. In science and related fields, refers to testing systematically under controlled conditions in order to discover the qualities, behavior, or effects of the subject of the experiment.\n", + "discover 300444006 The process of reconstructing an existing object by starting with the final product and working through the design process in the opposite direction. It may involve disassembling and examining and analyzing the object or action in detail to discover the concepts involved in manufacture.\n", + "discover 300054687 Conducting diligent and systematic inquiry or investigation into a subject or question, especially in order to discover or revise facts or theories.\n", + "discover 300434911 Devices comprised of acoustic receivers positioned at right angles to one another and attached to a shaft that is held by the user. The sound collected by these horns is conducted to ear-pieces through rubber hoses. Developed to discover the position of the source of sounds in space, as invented ca.1880, particularly for use on ships to locate the position of foghorns.\n", + "discover 300254807 Recorded results of diligent and systematic inquiry or investigation into a subject made to discover or revise facts, theories, or applications.\n", + "dwarf 300266100 Family containing five genera, with 25 or more living species of dwarf, mouse, and fork-crowned lemurs, all from Madagascar, including the smallest living primates. The number of species cannot be precisely given, as new species continue to be discovered; they date from the Holocene.\n", + "dwarf 300386945 Assemblages of non-stellar objects that are gravitationally bound and orbiting a star or star system. Planetary systems may include one or more planets and other bodies, such as dwarf planets, moons, asteroids, meteoroids, comets, and cosmic dust.\n", + "dwarf 300310690 Members of a species of extinct hominin presumed to have lived on the Indonesian island of Flores and maybe elsewhere from 94,000 until 18,000 years ago, well within the time range of modern humans. Skeletal remains of an adult female and other individuals were found at the Liang Bua cave on Flores in 2004 by a team of Australian and Indonesian anthropologists. The species was around one third the size of modern humans, made tools, hunted dwarf elephants and other animals, cooked food, and is thought to have descended from H. erectus, a much older and larger hominin that may also be the ancestor of modern humans; the small size of H. floresiensis was perhaps the result of island dwarfing. Given that no H. erectus remains have been found on Flores, an alternative theory is that the species arrived on the island already small, perhaps having descended much earlier from a common ancestor of H. erectus.\n", + "dwarf 300386950 Planetary-mass objects that are neither a planet nor a moon. As defined by the International Astronomical Union (IAU), a dwarf planet is a celestial body in direct orbit of a star, massive enough for its shape to be controlled by gravitation, but it differs from a planet in that a dwarf planet has not cleared its orbital region of other objects.\n", + "dwarfs 300343714 Species of evergreen native to Oregon and elsewhere in the U.S., growing to 60 m (200 feet) in height and 6 m (about 20 feet) in diameter. It is a very hardy tree, having over 200 forms cultivated as ornamentals in North America and Great Britain. Many of these are dwarfs.\n", + "dwarfs 300263109 Large natural objects that orbit a star or a stellar remnant. Planets are not radiating energy from internal nuclear fusion reactions, are not a brown dwarfs, and are bigger than an asteroid. Planets are large enough to have become round due to the force of their own gravity, and dominate the neighborhood around their orbit, and are thus distinguished from dwarf planets.\n", + "eskimo 300016731 Styles belonging to Pre-Columbian Eastern Eskimo cultures.\n", + "eskimo 300016736 Styles belonging to Pre-Columbian Western Eskimo cultures.\n", + "eskimo 300102489 Refers to the culture of the Yup'ik, a Western Eskimo group of Siberian Asia and of Saint Lawrence Island and the Diomede Islands in the Bering Sea and Strait. The Yup'ik are culturally related to the Chukchi.\n", + "eskimo 300411929 Family of languages spoken in Greenland, Canada, Alaska (United States), and eastern Siberia (Russia), by the Eskimo and Aleut peoples.\n", + "eskimos 300017437 Whenever possible, use the specific tribal name. The general term \"Native American\" is widely used in the United States, but many groups now prefer \"American Indian\" or \"Indigenous American.\" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term \"First Nations.\" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use \"Amerindian (culture).\"\n", + "eskimos 300389818 Broadly, the cultures of any native peoples of North America, Central America, South America, or the West Indies who are considered to belong to the Mongoloid division of the human species. For the cultures of native peoples of the United States and Canada, excluding the Eskimos and Aleuts, use \"Native American (culture).\" For the indigenous peoples of Canada use the term \"First Nations.\"\n", + "eskimos 300400856 Religious beliefs and sacramental practices of the indigenous peoples of the United States and Canada, excluding the Eskimos and Aleuts.\n", + "ethnic group 300055303 Restriction or denial of residential occupation, tenancy, or ownership because of prejudice based on such factors as age, sex, sexual preference, race or ethnic group, or social or economic status.\n", + "ethnic group 300438784 Cultures and styles of the Seediq people lived in Taiwan. In 2008 Seediq was officially recognized as an ethnic group distinct from the Truku people. The Seediq people primarily live in Renai Township, Nantou County and Hualien County. The Seediq language is constituted by three dialect clusters: Tada, Tgdaya and Truku. The traditional life centers on gaya (waya) and the belief in utux, while their social protocol has evolved through the encounter with the modern state and Christianity.\n", + "ethnic group 300435431 An indication of the tribe, band, ethnic group, linguistic group, cultural group, civilization, religious group, nation, country, city-state, continent, or general region from which the work originated.\n", + "ethnic groups 300025929 Smaller groups within a larger society that are the objects of prejudice or discrimination from the majority. For groups distinguished from the majority by their national, religious, linguistic, cultural,or sometimes racial background, use \"ethnic groups.\"\n", + "ethnic groups 300054316 The scientific, historic, or comparative study of the origins, characteristics, and functions of human cultures and societies. For the study of the history and culture of ethnic groups within a larger cultural or social order, use \"ethnic studies.\"\n", + "ethnic groups 300054447 Branch of psychology dealing with the minds and behavior of ethnic groups.\n", + "ethnic groups 300443479 A term used to describe that portion of all people, primarily in the United States, but perhaps used more widely, who are black, that is, dark-skinned peoples of Africa, Oceania, and Australia or their descendants, without regard to perceived actual skin tone. Indigenous refers to people of ethnic groups native to the Americas. People of color being a broad term for any non-Anglo-Saxon people.The term BIPOC is meant to be inclusive of those who are affected by racism, discrimination, or oppression based on ethnicity or race-based tropes.\n", + "ethnicity 300417373 Relating to, or comprising more than one distinct differentiated people based on socially defined characteristics, ethnicity, language, or culture. This term is applied both to groups of people or to individuals.\n", + "ethnicity 300449148 Culture and styles of British citizens or residents of either African or African-Caribbean origin or descent. Black British is one of various self-designation entries used in official UK ethnicity classifications.\n", + "ethnicity 300265422 The belief systems, values, philosophical systems, knowledge, behaviors, customs, arts, history, experience, languages, social relationships, institutions, and material goods and creations belonging to a group of people and transmitted from one generation to another. The group of people or society may be bound together by race, age, ethnicity, language, national origin, religion, or other social categories or groupings.\n", + "ethnicity 300400818 Holidays associated with a particular culture or ethnicity.\n", + "ethnicity 300016281 The style, culture, and ethnicity of a people of Angola who comprise two subsets with different origins, but related languages.\n", + "ethnicity 300435249 General designation for the race, ethnicity, styles, culture, and heritage of people of sub-Saharan African origin or descent in places outside Africa, or of members of any dark-skinned group of peoples, including those of Australian Aboriginal origin or descent.\n", + "ethnicity 300263154 Styles, cultures, and ethnicity of the region of the Lower Kasai river, primarily in today's Democratic Republic of the Congo. is GT, need concept\n", + "ethnicity 300443479 A term used to describe that portion of all people, primarily in the United States, but perhaps used more widely, who are black, that is, dark-skinned peoples of Africa, Oceania, and Australia or their descendants, without regard to perceived actual skin tone. Indigenous refers to people of ethnic groups native to the Americas. People of color being a broad term for any non-Anglo-Saxon people.The term BIPOC is meant to be inclusive of those who are affected by racism, discrimination, or oppression based on ethnicity or race-based tropes.\n", + "ethnicity 300443481 A rubric that encompasses and recognizes differences that may include ideas about race, gender, religion, sexual orientation, ethnicity, nationality, class, language, disability, or political perspective, and how these differences relate to justice, impartiality, and fairness with the procedures, processes, and distribution of resources by institutions or systems, and outcomes that ensure that institutional structures are truly inclusive off all constituencies.\n", + "exotic 300263554 Paintings in which the primary subject is an animal, generally a dog, horse, or other prized pet or livestock, or an exotic wild animal. The subject genre was highly developed in 18th-century European painting.\n", + "exotic 300263144 Comics in which the story or action is basically adventurous, often set in exotic locations and involving the main characters in travel.\n", + "exotic 300417767 Literature written by travelers, typically describing interesting or exotic places, the inhabitants, and adventures; often illustrated. The genre differs from \"travel guidebooks\" in not necessarily advising about lodging, food, and sights to see.\n", + "exotic 300020935 Refers to the style of art and architecture that flourished in Portugal and her colonies, beginning in the late 14th century and lasting into the mid-16th century. The style is named afer Manuel I, King of Portugal (ruled 1495-1521), and it developed as a national style and conscious rejection of Spanish style. The style is characterized by the merging of Late Gothic style with inventive references to Portuguese voyages, particularly in symbolism and lavish ornament. New themes include lush foliate and nautical designs, and references to the exotic, including Islamic art.\n", + "exotic 300265043 A type of still life painting featuring lavish arrangements of expensive foodstuffs and serving pieces. A typical banquet piece might include such luxury items as lobsters, oysters, exotic fruits, and decorated pies in raised crusts.\n", + "exotic 300106984 Refers to the second phase of the Orientalizing period, when curvilinear patterns and exotic motifs had replaced the earlier style and themes of the Geometric period.\n", + "exotic 300018959 A style of painting in India created by descendants of Mughal artists for the British in the late eighteenth and early nineteenth centuries. The artistic centers of this style were Delhi in the north, Lucknow, Calcuta and Patna in the east, and Madras and Thanjavar in the south. The subject matter of these 'Company paintings' consisted of flowers, animals, caste groups, festivals, and scenic spots; the techniques were adapted from European watercolors. The names derives from the East India Company, with which the patrons of the Company style were often associated. The patrons tended to have a genuine scientific interest in the Indian culture and environment rather than a passing curiosity about the exotic.\n", + "exotic 300113602 Period, culture, and English style in architecture and decorative arts from the restoration of Charles II in 1660 to the arrival of William and Mary in 1688. Characterized by opulent Baroque forms and motifs, it was influenced by artistic trends in Holland and France and the appearance of exotic imports of Japanese lacquer and Indian chintz. Architectural elements include spiral columns, hipped roofs, pediments, and sculptural figures, while the significant development in decorative arts was the taste for veneered walnut furniture.\n", + "exotic 300263588 Highly decorated bindings, usually covered in red morocco, tooled in gold with elaborate Rococo-style borders, areas of criss-crossed or dotted lines, and exotic motifs of animals, plants, and human and mythical figures. Motifs inspired by Chinese and Chinese export porcelain, such as dragons, flowers, and birds, are also common.\n", + "exotic 300020085 Refers to the ancient Greek period and style that followed the Geometric period and existed from around 725 BCE to around 650 BCE, overlapping with the early portion of the Archaic period of Greek history. It developed in Corinth and spread throughout Greece, to Etruria, and to other places with connections to Greece. It grew out of greatly expanded Greek trade and the subsequent influence of Near Eastern and Egyptian cultures. It is characterized by the abandonment of the geometric shapes and stick figures of the Geometric period to favor curvilinear forms, fleshy figures, and new themes, including exotic animals and monsters, such as sphinxes and griffins.\n", + "first world 300203949 Rifles specially designed for particular target shooting matches in which artificial supports were not used, originating in Germany in the 15th century and popular in the United States from the early 19th century until the First World War. They are characterized by long, heavy octagonal barrels, often with extra weight at the muzzle, palm rests, double set triggers, thick stocks, and very high quality, accurate sights.\n", + "first world 300204022 Bombs designed to be dropped from aircraft, first seriously developed during the First World War.\n", + "first world 300449024 Describes nations of the world that are considered economically and technologically advanced. Generally consider this more current and accurate than \"First World.\"\n", + "first world 300438588 German Expressionism consisted of a number of related creative movements in Germany before the First World War that reached a peak in Berlin during the 1920s. These developments in Germany were part of a larger Expressionist movement in north and central European culture in fields such as architecture, dance, painting, and sculpture. Der Blaue Reiter was a group of artists who were part of German Expressionism. The term as it is applied to cinema may be considered a separate concept.\n", + "first world 300206687 Emergency paper money issued during the first half of the 20th century, especially that issued by Germany and Austria during and shortly after the First World War.\n", + "first world 300448847 Refers to the style of artistic production in German colonies featuring a combination of French and native characteristics, particularly during the German Reich era between the late 19th century and the end of the First World War.\n", + "first world 300233909 Tactical fighter planes of the era from the First World War to the Second World War designed for speed and maneuverability during air battles.\n", + "first world 300127280 A term for a type of photographic portrait popular in the years before the First World War. Usually oval, finished with liberal airbrushing and colored with pastels.\n", + "first world 300258884 Military belts of heavy cotton woven fabric with metal fittings to carry equipment in the field, introduced during the First World War and later adapted for civilian use. Also, light cotton belts worn at the waist under military tunics or sashes to which sword slings may be attached, introduced around 1900.\n", + "first world 300235117 Colonies and other possessions in Africa and Asia of the defeated powers of the First World War, which were placed under the control of various different victor nations by the League of Nations.\n", + "footmen 300036879 Light shields or bucklers, borne instead of the heavy shield by targemen, footmen, archers, and sometimes horsemen. They were in common use by infantry soldiers from the 13th to the 16th century and in tournaments. They may be fitted concave to the body, fitted on the inside with two straps, the forearm passing through one and the hand grasping the other, or having a slot for placement of a weapon. \n", + "gay 300400510 General term for lesbian, gay, bisexual, or transgender / transsexual / transvestite attractions or behavior.\n", + "gay 300391091 Hydrometers for the determination of the alcoholic content expressed in Gay-Lussac degrees. The device was invented by French physicist and chemist Louis Gay-Lussac. \n", + "gay 300055475 Legal and social unions of a man and woman as husband and wife, or of the union of a gay couple. For the act or ceremony of instituting a marriage, use \"weddings (ceremonies).\" \n", + "gypsies 300404069 Animal-drawn caravans of the types used by gypsies or Irish travellers.\n", + "gypsies 300126370 Covered, nonmotorized animal-drawn vehicles equipped as traveling living quarters, particularly those used in the 18th and 19th centuries by small itinerant groups or individuals, such as gypsies, tinkers, or traveling salespeople; for motorized counterparts use \"motor homes.\"\n", + "gypsies 300111210 Refers to the culture of the modern nation of Romania, or in general to the cultures that have occupied the same area of southeastern Europe west of the Black Sea. It is occasionally also used to refer to the culture of the Romany or gypsies.\n", + "gypsy 300042168 Hungarian dulcimers consisting of a shallow trapezoidal box with from 20 to 35 courses of metal strings crossing two bridges, played while suspended from the player's neck by a strap or resting on four legs; popular in gypsy, folk, and nightclub bands.\n", + "handicap 300232777 Sailboats sufficiently alike or having differences under sufficient restrictions to enable them to race against each other as a class without the necessity of handicap allowances.\n", + "handicap 300232779 Racing sailboats built to a rule which allows hull and rig variations, but still allows boats built to the rule to race without handicap.\n", + "handicap 300006777 Places providing job training and vocational rehabilitation for the disadvantaged, whether due to physical handicap or lack of experience or education.\n", + "handicaps 300122943 Persons engaged in professional or voluntary service of a specialized nature concerned with community welfare and family or social problems such as arise from poverty, mental or physical handicaps, or maladjustment.\n", + "hermaphrodite 300389935 Belonging to or of the nature of a hermaphrodite, combining male and female characteristics.\n", + "homo 300024979 Members of the species Homo sapiens and their close extinct relatives, as distinguished from other animals, spirits, or other entities.\n", + "homo 300265711 Members of the species to which all modern human beings belong. Homo sapiens is one of several species grouped into the genus Homo, but it is the only one that is not extinct. The name \"Homo sapiens\" was applied in 1758 by Carolus Linnaeus, who distinguished humans from their close cousins, the apes. The large fossil record now contains numerous extinct species that are much more closely related to humans than to today's apes and that were presumably more similar to us behaviorally as well.\n", + "homo 300393250 The culture of the species of Homo sapiens.\n", + "homosexual 300265019 Ancient Greek vase inscriptions that take the form of \"so-and-so [is] kalos,\" kalos meaning handsome or beautiful, with an erotic connotation. Some such inscriptions are found on walls as well. The inscriptions are thought to indicate male homosexual love or a cult of celebrity, associated with pederastic courtships that were customary in ancient Greece; they probably reflect the emotions of the patron of the vessel rather than those of the vase painter. The names are usually those of teenage artistocratic Athenians. Those that can be associated with known historical figures have played a significant role in establishing the chronology of Attic vase painting, for they were presumably written when the named person was young. Kale inscriptions for women also exist but they are outnumbered by kalos inscriptions more than twenty to one; the women who are praised in these inscriptions were probably courtesans. The majority of kalos inscriptions are on vases produced between 550 and 450 BCE.\n", + "hottentots 300016575 Refers to the people and culture of southern Africa whom the first European explorers found in areas of the hinterland and who now live either in European settlements or on official reserves in South Africa or Namibia. Most Khoikhoi are either Nama or Oorlams, the latter term denoting remnants of the \"Cape Hottentots\" together with many of hybrid descent. The main Nama concentrations are the Bondelswarts, Rooinasie, Swartboois, and Topnaars; the main Orlams groups are the Witbooi, Amraal, Berseba, and Bethanie. The Khoikhoi are not easily distinguishable physically from the San, the Khoikhoi's slightly taller stature and decidedly longer and narrower head being the only marked differences.\n", + "hottentots 300265862 Primitive guitars of African peoples, particularly Hottentots and Bushmen. They usually are unfretted, have a belly made of skin, and three or four strings which are finger-plucked.\n", + "immigrants 300262962 Refers to the culture and style of works produced in the southern Louisiana bayou lands by the descendents French Canadian immigrants who were driven out by the British when they captured the French colony of Acadia (which was centered in what is now Nova Scotia) in the 18th century. One characteristic that defines the culture is the use of a distinctive patois, which comprises archaic French words and idioms derived from the English, Spanish, German, American Indian, and black cultures in southern Louisiana.\n", + "immigrants 300108469 Sections of towns or cities in which Chinese immigrants originally lived as a colony and to great extent followed their own customs; often, but not exclusively sea ports.\n", + "immigrants 300027808 Official records containing the names, dates of entry, ages, occupations, and other information about immigrants to a country, typically taken at the point of entry.\n", + "immigrants 300018071 Refers to the style and culture of seventeenth- and eighteenth-century German settlers in Pennsylvania and their descendants. Their culture is characterized by a retention of traditional German styles of cookery and craftsmanship, often recognized by distinctive decorative motifs, including geometric hex signs painted on barns and floral and other patterns stenciled on furniture and housewares. Some descendents drive horse-drawn buggies, wear simple, traditional clothing, and live according to strict religious principles. The large flow of immigrants from the Rhine area of Germany was encouraged by the religious tolerance of William Penn's colonial government. Immigrants were members of several groups, including Mennonites, Quakers, Amish, Moravians, Schwenckfelders, and Dunkers (or German Baptists); later immigrants included Lutherans and members of the Reformed churches.\n", + "immigrants 300179506 Buildings that house a variety of individual and family social, educational, and recreational facilities provided for recent immigrants or residents of underprivileged neighborhoods; especially in England and the United States since the late 19th century.\n", + "immigrants 300210746 Round, wedge-shaped caps with low, flat, soft crowns, with a short visor in the front. These are usually made of wool or tweed, but can be found in a variety of fabrics, and slight variations in styling. These are thought to originate in 15th century Northern England, though versions appear elsewhere in Europe, with variations in shape. They were originally worn and were associated with working class men, and became popular in the United States from the 19th century, introduced by immigrants from Ireland and England. They have gone in and out of fashion to the present day, with both men and women in many social contexts. Usage of the term has been extended to include caps of various shapes and styles appearing in portraiture, but should be reserved for the modern style and its obvious historical antecedents.\n", + "immigrants 300192795 People who depart from their native or usual country or region to live elsewhere. For those who come into a country or region from another to settle there, use \"immigrants.\"\n", + "immigrants 300264473 Objects plaited or woven from grain stalks, traditionally from the last sheaf to be cut in the field, intended to serve as a home over the winter for the spirit of the grain field, before being burnt or ploughed back into the field in spring to ensure the continuity of the harvest. The folk tradition originated in Britain and Ireland and was taken by immigrants to North America. The designs include human-like figures, one or more loops conjoined, or conical cages, and ribbons or rags are common enhancements. In the present time many are made for sale as crafts. \n", + "indian 300386028 The styles and cultures of various indigenous tribal populations located within the Indian subcontinent and retaining their ancient African/Austric languages, generally limited to those whose ancestral presence in the area precedes the Dravidian settlement of ca. 2000 BCE and various Aryan (Indo-European) invasions ca. 1500 BCE. In the constitution of India, in 1950 most of these groups were listed as Scheduled Tribes, targeted for social and economic development; used as the general term for the Indian scheduled tribes, who are usually descendents of these people.\n", + "indian 300017437 Whenever possible, use the specific tribal name. The general term \"Native American\" is widely used in the United States, but many groups now prefer \"American Indian\" or \"Indigenous American.\" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term \"First Nations.\" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use \"Amerindian (culture).\"\n", + "indian 300018863 Nationality, styles, and culture of the modern nation of India, or more broadly to cultures that developed on the subcontinent of India, which is bounded by the Arabian Sea, the Indian Ocean, the Bay of Bengal, and the Himalayn Mountains. It may also refer even more broadly to cultures of India, the East Indies, and the former British Indian Empire. It was formerly used less specifically to refer to any Oriental or Asian culture. Do not use this term to refer to the indigenous populations of North or South America; see \"Native American\" or other appropriate terms.\n", + "indian 300400847 Systems of diverse beliefs and practices of the culturally and linguistically related group of ancient peoples who inhabited the Iranian plateau and its borderlands, as well as areas of Central Asia from the Black Sea to Khotan (modern Hotan, China). In religion and culture, both the northern and southern Iranians had much in common with the ancient Indo-Aryan-speaking peoples of the Indian subcontinent, although there was much borrowing from Mesopotamia as well.\n", + "indians 300017596 Used to refer specifically to the material works of the Heiltsuk people that inhabit the village of Bella Bella, British Columbia. Often used erroneously to refer to the Heiltsuk people themselves. To describe material culture common to the Heiltsuk language speaking people in general, \"Heiltsuk\" is preferred. Note that scholarship as recent as 1998 uses \"Bella Bella\" to refer to the Heiltsuk people, or a sub-group therein. \"Bella Bella Indians\" is a term dating from ca. 1834 and is not based on aboriginal self-determination.\n", + "indians 300016954 Refers to the style and culture of a North American civilization that existed in the \"Four Corners\" area, where the boundaries of the states of Arizona, New Mexico, Colorado, and Utah intersect. The culture flourished from the first century CE to around 1300 CE, and descendants of this cultural group probably include the modern Pueblo Indians now living in New Mexico and Arizona. The style is noted for fine baskets, pottery, cloth, ornaments, tools, and great architectural achievements, including cliff dwellings and apartment-house-like villages, or pueblos. In some classification schemes, the modern Pueblo cultures are considered later phases of this people, though most schemes end this culture with the abandonment of the cliff dwellings around 1300 CE.\n", + "indians 300016773 Refers to a language group of North American Indians that encompasses many linguistic sub-groups and cultural groups. It is an arbitrary term derived from Lake Athabaska by Albert Gallatin in 1836 to refer to a culture that he believed were centered around this area. People belonging to the Athapaskan language group occupy vast areas of the subarctic region as well as areas in New Mexico and Arizona. Spelling of the term varies widely, and often appears in multiple forms in a single source. 'Athapaskan' has been in general use since 1930. 'Dene' or 'Na-Dené' is the self-determined descriptive term used by this group, and is sometimes used synonymously with Athapaska, though is also used to describe a larger category that includes Tlingit and Haida language groups.\n", + "indians 300017706 North American Indians of Iroquoian lineage who constituted one of the largest politically integrated tribes at the time of European colonization of the Americas. Their name is derived from a Creek word meaning 'people of different speech'; many prefer to be known as Keetoowah or Tsalagi. They formerly controlled approximately 40,000 square miles (100,000 square km) of the Appalachian Mountains in parts of present-day Georgia, eastern Tennessee, and the western parts of what are now North Carolina and South Carolina. Most members were forcibly removed from the Southeast by the U.S. government in the 1830s. Today the Cherokee Nation is a sovereign tribal government.\n", + "indians 300249545 Use generally to refer to various types of Native North American dwellings and ritual buildings, usually with regard to Plains Indians tribes; when possible use a more specific term.\n", + "indigenous 300262973 Refers to works produced by the Caucasoid Japanese people who are the indigenous inhabitants of the Japanese archipelago, the Kuril Islands, and part of Sakhalin Island.\n", + "indigenous 300386028 The styles and cultures of various indigenous tribal populations located within the Indian subcontinent and retaining their ancient African/Austric languages, generally limited to those whose ancestral presence in the area precedes the Dravidian settlement of ca. 2000 BCE and various Aryan (Indo-European) invasions ca. 1500 BCE. In the constitution of India, in 1950 most of these groups were listed as Scheduled Tribes, targeted for social and economic development; used as the general term for the Indian scheduled tribes, who are usually descendents of these people.\n", + "indigenous 300018564 Refers to the style and culture of Edo-speaking peoples living in Nigeria's Bendel state outside Benin City. While their languages are related, they are not all mutually intelligible. The Edo, however, all trace their origins to the Kingdom of Benin. Their ancestors migrated from Benin in a series of waves between the 9th and 18th centuries. These migrants intermixed with indigenous peoples and other settlers from neighboring areas, thus the arts of these peoples reflect a complex history of migration and cultural borrowing.\n", + "indigenous 300435341 Culture and ethnicity of the aboriginal people inhabiting the forest districts of Sri Lanka prior to the 6th century BCE. They adopted Sinhala and now no longer speak their own language. Ethnically, they are allied to the indigenous jungle peoples of southern India and to early populations in Southeast Asia.\n", + "indigenous 300380093 Refers to the culture of the indigenous Arctic people, also referred to as Lapp, who have inhabited portions of northern Scandinavia and Russia for thousands of years. \n", + "indigenous 300311237 Villages or settlements in parts of colonial South America, established by Spanish colonists or missionaries to accommodate the indigenous population in a controlled environment where they could be converted to Christianity and assimilated into European culture.\n", + "indigenous 300411917 Language family that developed among ancient indigenous peoples in South America, with branches in Central America, the Greater Antilles in the Caribbean and the Atlantic.\n", + "indigenous 300017583 The style and culture of the Iroquoian-speaking peoples of North America who emerged as a tribe around the north shore of Lake Ontario; believed to have been the most populous confederacy of Iroquoian-culture indigenous peoples of North America. \n", + "indigenous 300438808 Late Neolithic culture for which evidence is found in the historical Dobruja region, part of modern Romania and Bulgaria. It is named after the site at Baia-Hamangia, which was discovered in 1952. The status of this culture is unclear; it may represent an expansion of agricultural populations or a fusion with indigenous communities. Separate from evidence of settlements, cemeteries have been found.\n", + "indo 300019487 Refers to the style and period associated with the Indo-European speakers of Germanic languages whose origins are obscure, but who inhabited southern Sweden, the Danish peninsula, and northern Germany during the late Bronze Age. In later centuries various groups of Germanic peoples migrated south and west at the expense of Celtic peoples and other inhabitants. The artistic styles of the Germanic peoples are often associated with portable objects, including weapons and personal ornaments.\n", + "indo 300244536 Refers to the people, styles, and cultures originating in the general Caucasus region, which is the area between the Black and Caspian Seas, surrounding the Caucasus mountains, comprising roughly the modern nations of Georgia, Armenia, Azerbaijan, southern parts of Russia, and northeastern Turkey. It refers specifically to the Indo-European and Turkic cultures that have occupied the area since around the first millennium BCE. It takes its name from the Caucasus tribes that settled here; was home to Milesian Greeks, subsequently was invaded numerous times; legendary site of Jason's quest for Golden Fleece; the Caucasus mountains have traditionally been the boundary separating Europe from Asia; however, the area is more subject to Asian influence and so is more often grouped with Asia in modern scholarship.\n", + "indo 300386793 Ancient culture and style of a certain non-Indo-European people who flourished in South Asia, and who continue today in southern India, Sri Lanka, and elsewhere. Among distinguishing characteristics are architectural styles, distinctive clothing and hair styles, and as well as language. Many scholars believe that Dravidian languages are unrelated to any other extant language family, although there is extensive lexical borrowing, with Tamil being the oldest existing Dravidian language. Dravidian loanwords in Sanskrit date to around 1500 BCE, meaning the culture and its influence were firmly established prior to that date.\n", + "indo 300386794 Ancient cultures of the peoples associated with broad class of cognate languages that are still spoken over the greater part of Europe and extending into Asia as far as northern India. Included are the cultures associated with the existing and extinct language families of Anatolian, Hellenic, Indo-Iranian, Italic, Celtic, Germanic, Tocharian, Balto-Slavic, Armenian, Albanian, Illyrian, Venetic, Liburnian, Messapian, Phrygian, Paionian, Thracian, Ancient Macedonian, Ligurian, Sicel, and Lusitanian, among others.\n", + "indo 300400843 Religious beliefs and practices of the ancient Celts, an ancient Indo-European people, peaking during the 4th century BCE, extending across the length of Europe from Britain to Asia Minor. The religion included many male and female deities, some of whom were venerated only in a small, local area, but others whose worship had a wider geographical distribution.\n", + "indo 300404070 The culture and ethnic group of the traditionally itinerant people who originated in northern India but live in modern times worldwide, principally in Europe. Most Roma speak some form of Romani a language closely related to the modern Indo-European languages of northern India, as well as the major language of the country in which they live. It is generally agreed that Roma groups left India in repeated migrations and that they were in Persia by the 11th century, in southeastern Europe by the beginning of the 14th, and in western Europe by the 15th century. By the second half of the 20th century they had spread to every inhabited continent.\n", + "indo 300400847 Systems of diverse beliefs and practices of the culturally and linguistically related group of ancient peoples who inhabited the Iranian plateau and its borderlands, as well as areas of Central Asia from the Black Sea to Khotan (modern Hotan, China). In religion and culture, both the northern and southern Iranians had much in common with the ancient Indo-Aryan-speaking peoples of the Indian subcontinent, although there was much borrowing from Mesopotamia as well.\n", + "indo 300400836 Beliefs and practices of the inhabitants of the Italian peninsula from ancient times until the ascendancy of Christianity in the 4th century CE. It is influenced by religions of ancient Italic cultures, especially those of other Latin tribes, of the non–Indo-European Etruscans, as well as by that of the Greek colonizers of Sicily and southern Italy.\n", + "indo 300400848 Beliefs and practices of the ancient Slavic peoples of eastern Europe, a large branch of the Indo-European family of peoples.\n", + "indo 300388693 The Indo-European language in the Italic group that was originally spoken by small groups of people living along the lower Tiber River, and later spread around the world with the increase of Roman political power The oldest existing example of Latin dates to the 7th century BCE.\n", + "inuit 300435741 Groups of stacked stones or boulders in a figural form, constructed by Inuit individuals. Inuksuit are constructed to act as waypoints, message centers, spiritual veneration, or as hunting decoys. The oldest inuksuit date from 2400 to 1800 years ago.\n", + "inuit 300438494 Baskets constructed of baleen that is coiled around an ivory base. Often includes a lid topped with a carved, ivory finial; these finials are usually figurative, taking the forms of various Arctic animals. The first baleen baskets were woven by Inuit men in the 1910s following tourist interest. \n", + "inuit 300438480 Parkas characterized by broad shoulders and case on the back meant to carry an infant; created and worn by Inuit communities in North America. Often decorated with beadwork and fringe detailing. \n", + "inuit 300017447 Refers to artwork produced by native Arctic culture, prior to European contact. For names of specific native peoples of the present, use descriptors such as \"Chugach,\" \"Inuit,\" or \"Katladlit.\"\n", + "inuit 300102550 Refers to products of the Inuit people living along the northern coast of Labrador, now part of Quebec and Newfoundland. Originally a hunting culture focused on bowhead whales.\n", + "inuit 300017458 One of several groups of Inuit who live on the Arctic coast of Canada west of Hudson Bay.\n", + "inuit 300265652 Style and culture of the native people who live along the shores of Ungava Bay, on the south shore of Hudson Strait, and on the eastern coast of Hudson Bay. They exploit the resources of the vast area north of the treeline, especially sea mammals in the coastal waters, and also move inland to hunt caribou and at times penetrate the traditional Cree and Montagnais-Naskapi lands south of the treeline. Culturally close to the Inuit southeast of Baffin Island and to the Labrador Inuit, the Ungava nevertheless differ from these tribes in a number of linguistic and technological respects and in their social and religious customs.\n", + "inuit 300055999 Refers generally to the religious practices of some northern Asian peoples who believe that good and evil spirits inhabit the world and can be summoned or heard through inspired priests acting as mediums. Shamanism is also found amongst the pre-Chrisitian Lapps, the Inuit, the Plains Indians of North America, some Australian Aborigines, and some other peoples. The term was originally used by the Tungus people of Siberia.\n", + "madras 300265171 Refers to a type of Chinese folding screen that was typically very large, as tall as ten feet in height and twenty in length, with twelve panels of lacquered and gilded wood. Coromandel screens feature incised lacquer decoration and often have wide borders around the main design. The name comes from a part of the southeastern Indian coast near Madras that was a transfer point for Far Eastern goods being shipped to Europe by England's East India Company. Coromandel screens were mainly made in China in the 17th and 18th centuries for the European market.\n", + "madras 300265173 Refers to a type of lacquerware made in central and northern China from the 17th century and particularly popular in the 18th century in European high society. Coromandel lacquerware is characterized by its incised decorations filled with brightly colored lacquer or oil paint. The name comes from a part of the southeastern Indian coast near Madras that was a transfer point for Far Eastern goods being shipped to Europe by England's East India Company. The most well-known Coromandel lacquerware are the large Coromandel screens. The term is sometimes used to refer to the technique of doing the lacquering. The Japanese were also familiar with the technique but rarely used it for their lacquerware.\n", + "madras 300018959 A style of painting in India created by descendants of Mughal artists for the British in the late eighteenth and early nineteenth centuries. The artistic centers of this style were Delhi in the north, Lucknow, Calcuta and Patna in the east, and Madras and Thanjavar in the south. The subject matter of these 'Company paintings' consisted of flowers, animals, caste groups, festivals, and scenic spots; the techniques were adapted from European watercolors. The names derives from the East India Company, with which the patrons of the Company style were often associated. The patrons tended to have a genuine scientific interest in the Indian culture and environment rather than a passing curiosity about the exotic.\n", + "madras 300021637 Refers to the style and period that coincided with the rule of Murad I, son of Orhan, 1362 to 1389. During this period some new mosques were constructed at Bursa and the sultan is recorded as having employed Christian workmen. In 1366, Murad I began the construction of a kulliye, or charitable complex. It consisted of mosque-madras, a thermal bath of Byzantine origin, a large soup kitchen, and a school. Completed in 1385, the mosque was of the cross-axial form with four chambers, two of them having large fireplaces to shelter visiting dervishes. Under the central dome, stood a fountain for ritual ablutions before the raised mosque section. A unique feature of this building is the octagonal domed chamber over the mihrab, the niche in a mosque wall indicating the direction of Mecca.\n", + "madras 300417391 Refers to the modern art movement that emerged in the 1960s at Madras, the present-day Chennai in South India. Within a larger context of post-independence search for identity, the Madras School of Arts and Crafts played a pivotal role in this regional art movement. Led by the School’s principal K.C.S. Paniker and teacher S.Dhanapal, the Madras Art Movement sought to rethink strategies for deploying traditional regional art forms while maintaining modern sensibility and expressions. The artist-teachers along with students creatively interacted with the vernacular art of the region. The city Madras became an artistic center attracting artists from the southern states of India, where artists drew inspiration from the cultural traditions of their native regions, such as folk and tribal culture, and interpreted them with techniques and tools that were modern.\n", + "maroon 300053490 An iron process for making prints using a light-sensitive emulsion of a ferric salt and silver nitrate. When developed, a metallic silver image is formed; various developers can produce black, brown, purple, or maroon tones.\n", + "maroon 300013626 A permanent, deep red pigment containing cadmium. Earliest pigments were composed of pure cadmium sulfoselenide, first patented in Germany in 1892. Variations in the proportions of the cadmium and selenide produce as range of colors from orange to dark maroon. By 1926, cadmium reds were being co-precipitated with barium sulfate to form less expensive cadmium lithopone pigments.\n", + "maroon 300311175 Synthetically prepared red iron oxide pigment. It is a permanent pigment, having good tinting strength and good oil-drying properties, and ranging in color from scarlet to maroon. \n", + "maroon 300443390 Style and culture of a community or group of formerly enslaved Africans and Amerindian peoples and their descendants who fled, resisted, or rebelled against enslavement and found freedom in remote regions near where they had been forcibly relocated. Many of these groups have survived in the Caribbean and the Americas. Note that this community of people did not originally refer to themselves as “Maroon,” though some of their contemporary descendants have adopted the term, while others may consider it pejorative.\n", + "maroon 300435259 Genus containing around 50 species of annual herbs; native to southwestern North America, tropical America, and South America, but cultivated elsewhere. Noted for feathery foliage and flowers in various shades of yellow, orange, and maroon. It was regarded as the flower of the dead in pre-Hispanic Mexico, and is still widely used in the Day of the Dead celebrations. A few species are cultivated in Nepal, India, and Thailand, used in garlands and decoration for weddings, festivals, and religious events. \n", + "mestizo 300107836 Refers to a style of architecture built from the 16th to the 19th centuries in the mountainous region of southern Peru. It is characterized by the use of local volcanic tufa or sillar and an integration of Creole, Mestizo, and Pre-Columbian styles and motifs such as maize, cantuta flowers, birds, fish, and mythic figures into Baroque relief. In sculpture, it refers to 17th century Mestizo Baroque relief styles characterized by careful incisions in the surface that generate a tapestry-like effect.\n", + "metis 300265506 Style and culture of the tribe of Ojibwa and Metis peoples based on the Turtle Mountain Indian Reservation in Belcourt, North Dakota.\n", + "metis 300265512 Refers to the culture of the Metis, peoples of mixed French-Canadian and Native American ancestry.\n", + "mongoloid 300017437 Whenever possible, use the specific tribal name. The general term \"Native American\" is widely used in the United States, but many groups now prefer \"American Indian\" or \"Indigenous American.\" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term \"First Nations.\" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use \"Amerindian (culture).\"\n", + "mongoloid 300018777 Refers to the Eneolithic culture established in the steppes of the Minusinsk basin by Mongoloid peoples probably of Northern Siberian descent, from the beginning of the 2nd millennium BCE. Tombs have revealed a variety of stone sculptures.\n", + "mongoloid 300389818 Broadly, the cultures of any native peoples of North America, Central America, South America, or the West Indies who are considered to belong to the Mongoloid division of the human species. For the cultures of native peoples of the United States and Canada, excluding the Eskimos and Aleuts, use \"Native American (culture).\" For the indigenous peoples of Canada use the term \"First Nations.\"\n", + "mongoloid 300389501 Large language family of Eurasia, comprising languages and major dialects spoken by Caucasoid and Mongoloid populations in a territory extending from northern and central Europe in the west, to western and southern Siberia.\n", + "moor 300250079 Members of a species of large sedentary birds found in northern Eurasia in open moor and bog areas adjacent to forests, noted for having a group display in the spring.\n", + "moor 300140253 French term of uncertain derivation denoting decorative candlestands; original type had a circular top and a central standard, often in the form of a Moor, or, as the taste for exoticism increased, of a negress or Indian. In Louis XV and Louis XVI periods guéridons became small movable tables.\n", + "moor 300011200 Light silver-gray granite usually from one of four areas between Bodmin Moor and Land's End in Cornwall, England, the most important quarries being between Falmouth, Camborne, and Helston.\n", + "moor 300120786 Structures built generally parallel to the shoreline so that vessels may moor alongside to receive or discharge cargo or passengers. For similar loading and unloading places built to extend from the shoreline out over water, use \"piers (marine landings)\"; if such places are artificial solid banks or shoreline extensions built parallel to the shoreline, use \"quays.\" \n", + "moors 300298733 Hard leather shields used by light calvary and designed specifically for riding riding with a short stirrup with knees bent. They were originally of a round or heart shape, then generally created in the shape of a pair of overlapping ellipses or ovals. They were originally used by the Moors, then by Spain; the form came to North America when Cortés entered Mexico in the early 16th century.\n", + "moors 300266843 A type of granite found in England, used as a building stone, and often gathered from the surface of moors (hence the name).\n", + "moors 300386937 Culture of the subject Muslims who, during the Christian reconquest of the Iberian peninsula from the Moors in the 11th to 15th centuries, were allowed to retain Islamic laws, customs, and religion and to live in their own quarters in return for owing allegiance and paying tribute to a Christian monarch.\n", + "moors 300020944 Refers to the style of architecture and decorative arts that developed in Spain and Portugal during the period when the Moors gradually lost control of the Iberian peninsula, roughly during the 12th to 15th centuries. The term is derived from the Arabic word for vassal and was originally applied to the work executed by Moslem craftsmen working for Christian masters in brick, plaster, wood, and tile work, though it is now applied to all later Medieval Spanish work in the Islamic tradition, and includes bookbinding, textiles, ceramics, ivory, furniture, and wood and metal inlay work. The style is characterized by Muslim forms and motifs such as arabesques, Kufic inscriptions, stalactite work, azulejo, and horseshoe arches.\n", + "mulattos 300198715 In general, the term usually refers to a culture or style produced by people who were born in the Americas or nearby islands, but who were descended from colonists or slaves, as distinguished from people who arrived directly from Europe or Africa, or who were descended from aboriginal populations. It is used to refer to the cultures of different populations in the context of different regions; its usage is often contradictory from region to region. It refers to the culture and styles produced by white people who had Spanish parents and were born in the Spanish territories of North and South America in the sixteenth through eighteenth centuries; their culture and social position were distinguished from residents who had been born in Spain. In modern usage in the context of Latin America, it may refer to the culture of people born locally but of pure Spanish extraction or specifically to traditions of old-line families of predominantly Spanish descent. The term may also refer to the culture of early South American blacks born in America, as distinguished from blacks brought directly from Africa. In Louisiana in the United States it refers to the culture of either French-speaking white descendants of early French and Spanish settlers or of mulattos speaking a form of French and Spanish patois. It may also refer to the culture of people in the West Indies who were born and naturalized there, but were of Spanish, French, or African descent; in modern usage in the context of the Caribbean, it is often used to refer to Caribbean culture in general, including elements from European, African, Asian, and Amerindian sources.\n", + "métis 300438369 Blankets comprising a cloth or velvet covering with cloth ties on the underside made to cover the front and sides of a dog's body. Usually richly decorated in floral beadwork and cloth fringe, with bells placed along the center cut of the blanket. Used to protect sled dogs and to herald the sled's arrival. Originated with the Métis and later spread to Athabaskan communities.\n", + "métis 300438439 Fingerwoven sashes worn by Métis and First Nations individuals. Also known as assumption sashes due to their production in L'Assomption, Québec in the 19th century. Patterning varies, but often features an arrowhead design using red, green, yellow, blue, and white colored yarns. Currently, the sash has become a symbol of Métis identity.\n", + "métis 300438364 Cloth or velvet bags usually richly decorated with beadwork, made distinctive by its bottom terminating in eight separate arms. Created by Métis and First Nations communities to carry ammunition, fire starters, and/or tobacco. Likely originated in the early 1800s amongst the Métis and spread to other Native North Americans across Canada and the United States.\n", + "métis 300438520 Long, rectangular bands of woven fabric terminating in woven streamers or tassles, usually wrapped around the waist. Woven by using one's hands without the use of a loom, joining lengthwise and sideways threads together. Often used in Native North American and Métis regalia.\n", + "native 300404766 General term for Native North American period and culture dating approximately 200 BCE–500 CE, characterized by a shift of settlement to the interior of North America, an expansion of local and inter-regional trade, finer ceramics, and a shift to more elaborate burial practices for important people.\n", + "native 300017762 Cultures and styles of the more western Pueblo Native American people in the southwestern United States, particularly the Zuñi Desert Puebloans and the Hopi dry-farmers. The distinction between Eastern and Western Pueblo is based on the publications of certain scholars of the 1950s.\n", + "native 300017437 Whenever possible, use the specific tribal name. The general term \"Native American\" is widely used in the United States, but many groups now prefer \"American Indian\" or \"Indigenous American.\" This concept is typically reserved to refer narrowly to the cultures of the native peoples of the United States and Canada, excluding the Eskimos and Aleuts. For the indigenous peoples of Canada use the term \"First Nations.\" For the broader concept of the cultures of any native peoples of Central America, South America, North America, or the West Indies who are considered to belong to the Mongoloid division of the human species, use \"Amerindian (culture).\"\n", + "native 300018863 Nationality, styles, and culture of the modern nation of India, or more broadly to cultures that developed on the subcontinent of India, which is bounded by the Arabian Sea, the Indian Ocean, the Bay of Bengal, and the Himalayn Mountains. It may also refer even more broadly to cultures of India, the East Indies, and the former British Indian Empire. It was formerly used less specifically to refer to any Oriental or Asian culture. Do not use this term to refer to the indigenous populations of North or South America; see \"Native American\" or other appropriate terms.\n", + "native 300017554 General reference for the culture and styles of the Iroquois-speaking Native North American tribe called Tuscarora. Their name derives from an Iroquoian term for “hemp gatherers”; they were noted for their use of indigenous hemp for fiber and medicine. They coalesced as a people around the Great Lakes at about the time of the rise of the historic Iroquois tribes' five nations that was based in the area of present New York state. At the time of European settlement in the 16th century, the Tuscarora primarily occupied what is now North Carolina. Today, the Tuscarora are federally recognized and hold lands in New York state.\n", + "native 300389818 Broadly, the cultures of any native peoples of North America, Central America, South America, or the West Indies who are considered to belong to the Mongoloid division of the human species. For the cultures of native peoples of the United States and Canada, excluding the Eskimos and Aleuts, use \"Native American (culture).\" For the indigenous peoples of Canada use the term \"First Nations.\"\n", + "native 300056460 An outdated designation formerly used for the architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead other terms, such as \"vernacular architecture,\" or use the most specific name known for the culture of origin.\n", + "native 300438519 Style and culture of an Algonquian-speaking Native American tribe located in Long Island, New York. Have also been referred to as the \"Poospatuck\" in reference to the reservation the Unkechaug live on (Poospatuck Reservation, NY). \n", + "native 300056500 An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead \"indigenous art,\" \"tribal art,\" or the most specific name known for the culture of origin. Distinct from \"primitivism,\" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.\n", + "oriental 300055970 Refers to a philosophy developed by Plotinus in Alexandria in the 3rd century CE that consists of a modified version of Platonism combined with aspects of Judaic and Christian thought and possibly Oriental mysticism. Neo-Platonism holds that there is one source from which all existence comes from and with which an individual soul can be mystically united; it also emphasizes the plurality of levels of being, with the physical universe perceptible to the senses being the lowest. Neo-Platonism developed in a variety of forms over many centuries and it has enjoyed numerous revivals and modifications throughout history.\n", + "oriental 300021521 Refers to the art and culture associated with the Islamic dynasty of this name that was founded in 750, when it overthrew the Umayyad caliphate. The Abbasids were a Meccan family descended from Abbas, Muhammad's uncle. Their headquarters were in Mesopotamia and they founded the city of Baghdad in 762. Persian ideas prevailed during this period and the Abbasids ruled in great splendor as Oriental monarchs. Encouraging intense intellectual and artistic activity, many palaces and mosques were built and the production of luxury items became an industry. A unified style of art developed, inspired by ancient Persia rather than Christian Syria. The ruined city of Samarra, occupied by the Abbasids in the 9th century, is a prime example of this influence, especially in the Sassanian construction methods. Samarra is noted for its ornamental stucco, particularly the so-called 'bevelled' manner of decoration derived from Scythian-Siberian abstract design. Highly valued Chinese porcelain was imitated by potters of the period; the results were distinctly Islamic, however, with Arabic inscriptions and designs. Abbasid textiles also assumed an identifiable Islamic character. The vast empire became unwieldy and as its central administration weakened, rival caliphates were established. Although the Abbasids continued to rule part of the Islamic world until 1258, their dominance only lasted until the mid-10th century.\n", + "oriental 300022022 Oriental Orthodox Christian religion of predominantly Muslim Egypt. Egyptians before the Arab conquest of the 7th century identified themselves and their language as Aigyptios in Greek (Westernized as Copt) and later when Egyptian Muslims stopped calling themselves Aigyptioi, the term became the distinctive name of the Christian minority. Since the 5th century these Christians have been Monophysites, meaning that they acknowledge only one nature in Christ. Apart from the Monophysite question, the Coptic and the Eastern Orthodox churches agree regarding doctrine. Services are almost entirely conducted in Arabic and the service books, using the liturgies attributed to St. Mark, St. Cyril of Alexandria, and St. Gregory of Nazianzus, are written in Coptic (the Bohairic dialect of Alexandria), with the Arabic text in parallel columns. After the 1890s the church devised a democratic system of government, led by the patriarch who lives in Cairo. Outside of Egypt, there are a few Coptic Orthodox churches in the Holy Land and a Coptic bishopric in Khartoum, Sudan. The Ethiopian, Armenian, and Syrian Jacobite churches are in communion with the Coptic Orthodox Church. There is an impressive body of Coptic religious art and the church is known for its vital system of schools. There are over three million Copts and, although a minority, are well represented in Egyptian professional life. Copts have suffered and continue to suffer occasional persecution. With reference specifically to the Early Medieval period in Egypt, use \"Coptic (period).\"\n", + "oriental 300374835 Species of large, deciduous timber and forest tree originally found throughout North America. However, a fungus, Oriental chestnut blight, imported in the early part of the 20th century killed most of the trees. Before the species was devastated, it was one of the most important forest trees throughout its range. There are now very few mature specimens of the tree within its historical range, although many small sprouts of the former live trees remain.\n", + "oriental 300018863 Nationality, styles, and culture of the modern nation of India, or more broadly to cultures that developed on the subcontinent of India, which is bounded by the Arabian Sea, the Indian Ocean, the Bay of Bengal, and the Himalayn Mountains. It may also refer even more broadly to cultures of India, the East Indies, and the former British Indian Empire. It was formerly used less specifically to refer to any Oriental or Asian culture. Do not use this term to refer to the indigenous populations of North or South America; see \"Native American\" or other appropriate terms.\n", + "oriental 300022024 An Oriental Orthodox Christian religion based in the Eastern Mediterranean. By tradition it derives from an early Christian community established in Antioch by St. Peter the Apostle. It uses the oldest surviving liturgy in Christianity, the Liturgy of St. James the Apostle, which is celebrated in Syriac, a dialect of Aramaic spoken by Jesus and the apostles. The church is led by the Syriac Orthodox Patriarch of Antioch. The group has historically been called \"Jacobites\" after St. Jacob Baradaeus, bishop of Edessa, who organized their community in the 6th century; however, they reject that name because they trace their beginnings instead to St. Peter. \n", + "page 300252610 Titles of works or major divisions of works, such as parts or chapters, when they appear at the beginning of the first page of the text, often though not always set below the normal level of the first line of the page. Use also for the titles of musical scores when they appear immediately above the opening bars of the music.\n", + "page 300123430 Pictorial images, usually drawings, that are humorous or that use wit and satire to comment on contemporary events, social habits, political trends, or other topical subjects, often executed in a broad or abbreviated manner. Originally referred to full-page illustrations in a circulating paper or periodical, especially when comical and relating to current events. \n", + "page 300179434 Groups of works brought together such as to exemplify the work of an artist or student. Also, groups of art works or other visual materials (often by one artist) such as photographs or prints, issued or housed together in a portfolio; they often include a loose title page or text introduction.\n", + "page 300196838 Outer sheets or boards that are part of, or are attached to, groups of leaves, whether a substantial block or a single gathering; sometimes simply the first page of a document, as for example of a leaflet, if it is designed as distinct from the body of the document. Designed to protect the text block or gathering within, and often carrying information about it such as the title, and decoration.\n", + "page 300417205 Titles or names that have been supplied by the cataloger in cases where supporting information or description of a work lacks a title. Constructed titles may be derived from other text in or on the work or invented as a descriptive title or name by the cataloger. In book cataloging, an example is when a title proper is not included on a title page.\n", + "page 300417193 Words or phrases, often descriptive or evocative, used to identify or provide reference to a work, including physical works, performances, literary works, and conceptual works. May apply to individual items or works, or to groups or series of items, in any medium. Titles may also be initials, numbers, or symbols. Examples are titles or names of works of art and architecture. For numeric or alphanumeric IDs or codes for uniquely identifying a work, prefer \"identification numbers.\" To refer specifically to titles printed or inscribed on a book or other object, such as on the title page, prefer \"titles (partial documents).\"\n", + "page 300417202 Titles or names of works that are written, stamped, or printed on the work. For works of art, it may include any part of an inscription that is clearly intended by the creator or publisher to serve as a title or that the cataloging institution wishes to record as a title. For manuscript or book cataloging, it is the title on the title page or found elsewhere in the book.\n", + "pages 300264330 Notebooks of usually ruled pages used by school children for the writing or drawing of exercises.\n", + "pages 300055033 Pages on the right-hand side, recto of a leaf, at the beginning of a book where the bibliographic information about the work is provided, displaying the book's title and usually the author's name, the publisher, and sometimes the date of publication. Where more than one page giving particulars of the title are present, that giving the fullest information is the title page. \n", + "pages 300028710 Inscriptions historically placed at the end of a book and containing the title, the publisher's or printer's name, date and place of printing. Sometimes they include claims by the publisher or printer for their role in the production of the work in order to protect their property from the depredations of rival printer-publishers. By about 1480, part of the contents of the colophon was transferred to the blank cover page at the front of the book, thereby initiating the title page as it is now known today. In modern usage in most countries, the colophon now appears on the page opposite the title page and consists of a one-sentence statement that the book was printed by a given printer at a given location. Colophons stating the typeface, paper, and other production details of fine editions are sometimes still placed on the last page, however. For similar inscriptions on the final pages of manuscripts and incunabula, use \"explicits.\"\n", + "primitive 300016925 Refers to the second of three phases in the development of Cochise culture, dating from around 4,000 BCE to around 500 BCE. It is characterized by the creation of projectile points, presumably for hunting, and probably also by the development of farming, suggested by the remains of a primitive form of maize.\n", + "primitive 300019289 Refers to the period and style of a primitive flake-tool tradition of France and Israel characterized by striking flakes from a flint core in alternating directions, the cores being saved and used as choppers. The style is believed to be related to the Clactonian industry.\n", + "primitive 300019508 Refers to the period and style associated with the Lombards, a nomadic, Germanic people who were part of the Suebi group, lived in northwestern Germany in the first century CE, and started their southward migration in the fourth century. The term refers particularly to the Lombard conquest of much of the Italian peninsula, lasting from 568 until the 11th century in some areas. The style is first evident in portable objects, primarily personal ornaments and weapons, and later most notably in sculpture. The style is characterized by a flat, decorative effusion of symmetrically placed birds, animals, interlaces, geometric patterns, and lively, primitive figures that show Byzantine influence.\n", + "primitive 300056548 A term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art that was formerly designated primitive and other art made by people operating outside of mainstream art markets. Distinct from \"primitive art\" and \"primitive architecture,\" which are outdated terms formerly used for art and architecture of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups. For the Russian art movement, active from about 1905 to 1920, which combined influences from Russian folk art with ideas borrowed from Cubism and Futurism, use \"Primitivist.\"\n", + "primitive 300020074 Refers to a period and style of Greek art and culture that occurred from around 1100 BCE to around 900 BCE. It is characterized by the importation of objects and styles from the Levant and Egypt, a renewal of native Greek styles, and a general recovery from the upheavals caused when the Minoan/Mycenean world was violently overthrown in the 12th century BCE. Surviving artworks include simple fibulae, primitive clay figures, and pottery that is typically decorated with circles, arcs, triangles, and wavy lines, often executed with multiple brushes and placed in horizontal bands on various parts of the vessel.\n", + "primitive 300265683 Phylum of primitive multicellular aquatic animals. There are approximately 5,000 described species and inhabit all seas, where they occur attached to surfaces from the intertidal zone to depths of 29,000 feet or more. Early naturalists regarded the sponges as plants because of their frequent branching form and their lack of obvious movement. The animal nature of sponges was first described in 1755, and was confirmed in 1765 after observations revealed movement of their openings. In structure, function, and development, however, sponges are distinct from other animals. Many zoologists regard sponges as occupying an isolated position in the animal kingdom and classify them in the subkingdom Parazoa. Other sources consider sponges relatives of the invertebrate animal group coelenterates. Aquatic, chiefly marine animals of the phylum Porifera, varying greatly in size, shape, and color, and having a porous body and siliceous or calcareous internal framework, living permanently attached singly or in groups, feeding b filtering food particles from the water that enters their internal body channels through their pores. They are very simply organized with no mouth, digestive cavity, nerves, muscle, or true behavior, and sometimes are considered to be colonized protozoans rather than single multicellular organisms. For the light, porous, yielding fibrous skeletal matter of these animals, use \"sponge (material).\"\n", + "primitive 300264837 Refers to artists working in China beginning around 1100, and in Korea and Japan in later periods. They are characterized by being primarily scholars and gentlemen, which they held made them distinct from, and superior to, professional painters and craftsmen. They believed that an art work revealed the character of the person who painted it and that quality in art was dependent upon the moral rectitude and intellect of the artist. They typically integrated poetry, calligraphy, and simple monochromatic painting into a single work. Their works often had a learned literary content. They preferred calligraphic expressionism over realistic and detailed depictions, often making allusions to antique styles and using deliberately primitive or naive techniques. Motifs such as bamboo, plum, or flowers were used to showcase brushwork.\n", + "primitivism 300174254 Russian art movement, active from about 1905 to 1920, which combined influences from Russian folk art with ideas borrowed from Cubism and Futurism.(THDAT) For the deliberately unsophisticated and unschooled approach to artistic creation, use \"primitivism.\"\n", + "primitivism 300056500 An outdated designation formerly used for the art of certain people considered to be outside the spheres of influence of other, politically dominant cultural groups; was used especially concerning communities in sub-Saharan Africa, the Pacific Islands, and native tribal groups throughout the Americas. Use instead \"indigenous art,\" \"tribal art,\" or the most specific name known for the culture of origin. Distinct from \"primitivism,\" a term sometimes used for artistic styles or movements intended, often romantically or sentimentally, to emulate the appearance of art made by people operating outside of mainstream art markets.\n", + "primitivism 300143666 Religion and philosophical tradition originating in China, generally emphasizing individual freedom and spontaneity, laissez-faire government and social primitivism, techniques of self-transformation, mystical experience, and individual and government ethical responsibility. It is founded on the texts of the Tao-te Ching, Chuang-tzu, and Lieh-tzu. Later, the tradition diverged, resulting in strictly philosophical Taoism on the one hand, and religious Taoism on the other. The governing principle of the latter is the struggle to reach a state of 'immortality' through a strict regimen of dietary restrictions, breath control, meditation and visualization of the gods that inhabit the body, sexual control and discipline, the practice of theoretical internal alchemy (nei-tan) used to energize the Yin and Yang forces within the body, and the use of magic talismans. Successful devotees were known as hsien (Immortals).\n", + "pygmy 300016430 The collective style and culture of various African peoples whose adult males grow to less than 59 inches (150 cm) in average height, and who live in Cameroon, Equatorial Guinea, Gabon, Democratic Republic of Congo, Congo Republic, Central African Republic, Rwanda, and Burundi. Use of \"Pygmy\" for a culture is considered pejorative; where possible use instead the most specific name for the subgroup.\n", + "pygmy 300262764 Style and culture of the Pygmy-stature African ethnic group inhabiting the Tumbwe region of southeastern Democratic Republic of Congo.\n", + "pygmy 300260713 Style and culture of the African Pygmy ethnic group of the same name currently inhabiting the southeast Ituri Forest region of Zaire.\n", + "pygmy 300263793 Describes works produced by the African people of the same name living mainly in Burundi and Rwanda, but also in Uganda, Tanzania, and Democratic Republic of Congo. The Hutu came into the Great Lakes region around 1000 to 500 BCE. Among the resident Twa pygmy peoples, they established an agrarian society based on the family unit. They were gradually dominated by a feudal system headed by the aristocracy of the nomadic Tutsi people in the 14th or 15th century. The Tutsi monarchy in Rwanda was overthrown 1959-1961. The European colonial period created tensions between the two groups that remain problematic.\n", + "race 300264475 An individual person's conscious sharing of some kind of essential character with one or more groups of other people, such as a race, nation, social class, profession, or body of people organized into a group at some particular time for some particular purpose.\n", + "race 300265422 The belief systems, values, philosophical systems, knowledge, behaviors, customs, arts, history, experience, languages, social relationships, institutions, and material goods and creations belonging to a group of people and transmitted from one generation to another. The group of people or society may be bound together by race, age, ethnicity, language, national origin, religion, or other social categories or groupings.\n", + "race 300249198 Social, political, and economic system of racial segregation, assigning rights to classes of people based on their racial background, supremacy being granted to those of white European extraction, with laws limiting the political participation and economic advancement of those of African, Asian, and mixed race.\n", + "race 300449021 The idea that all individuals are equals and that whenever individuals behave positively or negatively this behavior is not judged as being representative of an entire race-based group. To be antiracist is to deracialize behavior.\n", + "race 300443479 A term used to describe that portion of all people, primarily in the United States, but perhaps used more widely, who are black, that is, dark-skinned peoples of Africa, Oceania, and Australia or their descendants, without regard to perceived actual skin tone. Indigenous refers to people of ethnic groups native to the Americas. People of color being a broad term for any non-Anglo-Saxon people.The term BIPOC is meant to be inclusive of those who are affected by racism, discrimination, or oppression based on ethnicity or race-based tropes.\n", + "race 300443481 A rubric that encompasses and recognizes differences that may include ideas about race, gender, religion, sexual orientation, ethnicity, nationality, class, language, disability, or political perspective, and how these differences relate to justice, impartiality, and fairness with the procedures, processes, and distribution of resources by institutions or systems, and outcomes that ensure that institutional structures are truly inclusive off all constituencies.\n", + "race 300055479 The condition in which different levels of caste, class, privilege, or status make up a society. A person's strata may be ascribed at birth or achieved. Factors involved in social stratification include gender, race, age, wealth, family relationships, education, occupation, marital status, and language.\n", + "races 300386795 Refers to the styles that arose under or were influenced by the ideals of the German Nazi regime (1933-1945), particularly regarding inhabitants of Germany and elsewhere who were of what the Nazis considered the white race of ancient Germanic origin, excluding those of Jewish heritage. The ideas have earlier origins, in the 19th-century writings of Joseph-Arthur de Gobineau and others regarding what they perceived as the inferiority of certain races.\n", + "second world 300233434 Mass-produced three-island vessels of 10,500 deadweight tons built to a specific design in the United States during the Second World War to carry general cargo and military supplies.\n", + "second world 300036935 Official nickname for a type of tube-shaped smoothbore portable rocket launcher, held atop the shoulder when fired, introduced as antitank weapons during the Second World War.\n", + "second world 300111551 Used to designate vegetable gardens cultivated to increase food production during the Second World War, especially in England and America.\n", + "second world 300232853 German subsurface attack vessels developed during the First and Second World Wars.\n", + "second world 300233909 Tactical fighter planes of the era from the First World War to the Second World War designed for speed and maneuverability during air battles.\n", + "second world 300228124 Small, multipurpose rugged military vehicles with four-wheel drive and one-quarter ton capacity, introduced in 1941; after the Second World War produced for civilian use as a trademarked marque.\n", + "second world 300201794 Protective garments consisting of overlapping plates of steel, aluminum, or bonded fiberglass attached within a nylon jacket. They were developed during the Second World War to protect aircraft crews against fragments from antiaircraft shells, and are now also widely used by ground combat personnel.\n", + "second world 300265774 Political ideology that advocates a transition to a socialist society, achieved gradually through the democratic process. Originally a form of Marxism, the movement grew out of the formation of the German Social Democratic Worker's Party in 1869, which eventually led to the Social Democratic Party of Germany. Its philosophy evolved and eventually rejected militarism, totalitarianism, and revolution as a means for political change. A main advocate of social democracy was theorist Eduard Bernstein, who parted ways with Marx and Engel, instead positing that democracy must be embraced in order to instill socialist changes. Following the Second World War, several social-democratic governments came to power, including those in West Germany and Sweden.\n", + "second world 300235120 Under the Charter of the United Nations, non-self-governing territories, primarily former mandates and colonies of the defeated powers of the Second World War, placed under the administrative authority of U.N. members and subject to regular inpection by U.N. missions.\n", + "second world 300265478 Broadly defined post-Second World War art movement named to distinguish it from 'classic' avant-garde movements such as Surrealism. \n", + "servant 300393209 The activity or condition of being employed as a servant attached to a household. \n", + "servants 300258978 Officials of monasteries and other religious communities in charge of provisions and supplies, especially of food, of the running of the kitchens, the work and conduct of servants and lay members, the purchase and delivery of goods, and all aspects of the management of the establishment that are not specifically assigned to others.\n", + "servants 300435318 A butler is the chief male servant in a large household; primary responsibilities may include managing the wine cellar, overseeing dining arrangements, supervising other servants, and greeting visitors.\n", + "servants 300136452 Servants or attendants who work in the household, often living in the same house as the family.\n", + "servants 300236032 Refers to state officers or servants, either of prominent households or individuals, who carry messages and announce proclamations, and often also keep the family's genealogical records and regulate the depiction of its coats of arms. Applies particularly to officials in Medieval and modern Europe who arranged ceremonial events, particularly tournaments, at which they had special charge of conveying challenges and regulating the use of coats of arms by combatants. From the 19th century onwards, the office's duties consist mainly of regulating a family's or organization's coat of arms and often of doing the blazonry of those arms as well. For visual artists whose works consists solely of depicting coats of arms, see \"blazoners.\"\n", + "servants 300411753 Uniforms for servants, of various historical design, informed by the employer's tastes and job requirements.\n", + "servants 300448974 The condition whereby a person supplies compulsory labor to another, due to obligation, imprisonment, or another reason. In modern usage, does not include the condition of voluntary employment for domestic servants, whether past or present.\n", + "servants 300150456 Ministerial offices, branches of public employment, or bodies of public servants concerned with some particular kind of work or the supply of some particular need in a society.\n", + "slaves 300311322 Coachmen in colonial Latin America, usually depicted stereotypically as black men, usually slaves, who drove calesas, or carriages. Their extravagant uniforms and ornamentation were indications of their owners' wealth. In Cuba, caleseros are distinctive characters of the colonial period and are usually portrayed in images as garishly dressed dandies.\n", + "slaves 300256825 Documents issued to freed slaves, attesting to their status.\n", + "slaves 300198715 In general, the term usually refers to a culture or style produced by people who were born in the Americas or nearby islands, but who were descended from colonists or slaves, as distinguished from people who arrived directly from Europe or Africa, or who were descended from aboriginal populations. It is used to refer to the cultures of different populations in the context of different regions; its usage is often contradictory from region to region. It refers to the culture and styles produced by white people who had Spanish parents and were born in the Spanish territories of North and South America in the sixteenth through eighteenth centuries; their culture and social position were distinguished from residents who had been born in Spain. In modern usage in the context of Latin America, it may refer to the culture of people born locally but of pure Spanish extraction or specifically to traditions of old-line families of predominantly Spanish descent. The term may also refer to the culture of early South American blacks born in America, as distinguished from blacks brought directly from Africa. In Louisiana in the United States it refers to the culture of either French-speaking white descendants of early French and Spanish settlers or of mulattos speaking a form of French and Spanish patois. It may also refer to the culture of people in the West Indies who were born and naturalized there, but were of Spanish, French, or African descent; in modern usage in the context of the Caribbean, it is often used to refer to Caribbean culture in general, including elements from European, African, Asian, and Amerindian sources.\n", + "slaves 300233279 Vessels engaged in transporting human beings for sale as slaves, sometimes designed specifically for the purpose.\n", + "slaves 300258488 Fighting men of ancient Rome, either professionals or slaves, captives, or condemned criminals, who fought to the death with other men or with wild animals as a form of public entertainment.\n", + "slaves 300005675 Houses or parts of houses occupied by slaves, who are people treated as the property of another person, whether by capture, purchase, or birth.\n", + "slaves 300417705 Objects or other gifts given to a person or place, or exchanged between two parties, as a sign of esteem and honor. May involve ritual and ceremony; in historical contexts, may involve slaves or animals.\n", + "third world 300264337 A religion that arose out of the Persian Islamic sect Babi in the 1860s, founded by Bahaullah who claimed to be the prophet foretold by Ali Mohammed Shirazi, the founder of the Babi sect. Bahaism emphasizes both social goals and spritual truths: the oneness of God, the unity of all faiths. Worship consists of daily prayers and scripture reading; Bahai houses of worship have proliferated throughout the world, especially in the Third World, and are typically centered around a school, hospital, orphanage, or similar institution. The governing body, called the Universal House of Justice, meets every five years and is based in Haifa, Israel.\n", + "third world 300262022 Generally meaning the state of being of mixed origin. In a social or cultural context, refers to the concept of individual or group self-identity or creative activity deriving from the interaction of two different societies or cultures, often within the context of Third World people encountering Western or Westernized people, or the formerly colonized meeting the colonizers.\n", + "traditional 300438466 Religious movement beginning in the 19th century based in Plateau Native North American spiritual practices. Smohalla, a Wanapum prophet and leader, developed the faith after receiving visions on how to remove white settlers from the Columbia River area. Followers believed adherence to traditional practices and peaceful opposition to colonization would revert society back to their pre-contact lifeways. The Dreamer religion continues to be observed today, with revival of Native culture and protection of the environment as major themes.\n", + "traditional 300193270 Refers to the culture, style, and movement of Mexican Americans in the United States, particularly as beginning in the 19th century, characterized by artistic and political discussions addressing social issues relevant to Mexican and Chicano communities. The movement is driven by a rediscovery of Pre-Columbian indigenous styles, the development of mural painting, and by cultural studies focussed on bi-culturalism and ethnic heritage and identity. The movement also reveals strong regionalist elements, promoting vernacular forms and techniques to expound traditional and contemporary iconography.\n", + "traditional 300165261 Religious movement and Jewish branch espoused by Zacharias Frankel (1801-1875) that endeavors to preserve particular elements and customs of traditional Judaism while allowing for limited modernization such as the support of the secular Zionist movement. This branch of Judaism is governed by the idea that Judaism defines Jewish culture and national identity, and therefore, religious customs and traditions such as dietary laws, the study of Hebrew, and the observation of Sabbath, must be upheld.\n", + "traditional 300443560 Heritage characterized by the continuity of the original function or the purpose for which it was originally established. Such heritage maintains the continuity of community connections, continues to evolve in the form of tangible and intangible expressions, and taken care through traditional or established means. \n", + "traditional 300264839 Nature reserves inhabited by indigenous peoples of Australia that have been designated as protected by the Australian Government. Traditional indigenous owners of the land enter into voluntary agreement with the Govenment to establish the boundaries of the area, in order to promote biodiversity and to preserve cultural resource conservation. An IPA is considered part of the National Reserve System of Australia.\n", + "traditional 300438843 Formal statements that recognize the unique and enduring relationships that exist between indigenous peoples and their traditional territories.\n", + "traditional 300438761 Mgay Bari is a festival restored by contemporary Truku people upon a common agreement. Mgay Bari is set up to strengthen the cultural integrity of Truku with the influx of Christian faith, the loss of their tradition and the movement petitioning for official recognition, in hopes of reviving the traditional Truku culture.\n", + "traditional 300417392 The term, specific to the discussion of Indian art and culture, relates to issues about the continuity of traditions. It was felt that the British administration and educational system in India were undermining the art and craft system in the country, which had had a continuity of development. Soon after independence, a number of government institutions and museums dedicated to rural arts and crafts emerged in India. Modern artists in the urban contexts also invested considerable attention to the contexts, techniques, and forms of traditional art practices. This engagement brought new questions on how to define tradition in the 20th century; how to reconcile the relationship between modern and traditional art; how to support a sustainable environment for traditional arts; and how these disappearing art forms might be preserved. Artists in Baroda were particularly interested in these questions, which translated into various institutional initiatives, Fine Art Fairs, research projects, and artist exchanges and workshops with artisans from rural contexts.\n", + "traditional 300417391 Refers to the modern art movement that emerged in the 1960s at Madras, the present-day Chennai in South India. Within a larger context of post-independence search for identity, the Madras School of Arts and Crafts played a pivotal role in this regional art movement. Led by the School’s principal K.C.S. Paniker and teacher S.Dhanapal, the Madras Art Movement sought to rethink strategies for deploying traditional regional art forms while maintaining modern sensibility and expressions. The artist-teachers along with students creatively interacted with the vernacular art of the region. The city Madras became an artistic center attracting artists from the southern states of India, where artists drew inspiration from the cultural traditions of their native regions, such as folk and tribal culture, and interpreted them with techniques and tools that were modern.\n", + "trans 300417316 Dougong refers to a unit consisting of a number of mortised bearing blocks (dou 斗), arms (gong 栱), tie-beams (fang 枋) and inclined beams (ang 昂). They are often used under the eaves, on beams, or on the tops of pillars.The first use of the term dougong as a compound word can be traced to the Sui dynasty translation of the Yaoshi rulai benyuan jing (Dharmagupta trans. 616 CE, Taishō 449): “The city-gate towers, walls and parapets, doors and windows, halls and pavilions, pillars and beams, blocks and bracket arms (dougong 斗拱), surrounding like a net, are all composed of the seven jewels.” After the Sui dynasty, dougong gradually became a set technical term and can be found in a number of different textual sources. The earliest known material evidence for dougong is the dragon-phoenix table-base excavated from the Warring States Period Zhongshan royal necropolis in Pingshan, Hebei province (ca. 310 BCE; ZHONG Xiaoqing, 2010：113-119). From the Han dynasty onward we have many extant examples of dougong in the visual record.\n", + "trans 300435025 Collages made of shells and other marine materials, arranged to make particular patterns or designs. Commonly made in the 19th century by artisans on Barbados and other Carribean islands for sale in the tourist trade. Many of these were bought by trans-Atlantic sailors as souvenirs for their families.\n", + "transvestite 300400510 General term for lesbian, gay, bisexual, or transgender / transsexual / transvestite attractions or behavior.\n", + "tribe 300435504 Culture of an Algonquian tribe that was historically considered to be a part of the Delaware, or Lenape, although they lived separately from the Delaware nation for most of their existence. Some scholars argue that the Munsee should not be considered Delaware because of some stark differences in dialect. The United States referred to the Munsees as a separate tribe in the Treaty of Fort Industry.\n", + "tribe 300435431 An indication of the tribe, band, ethnic group, linguistic group, cultural group, civilization, religious group, nation, country, city-state, continent, or general region from which the work originated.\n", + "tribes 300438772 Cultures and styles of the Amis people lived in Taiwan. The Amis people refer to themselves in two ways: Pangcah meaning “we people” is used in regions north of Taitung, and Amis meaning “northerners” is used in the south. The denomination has to do with routes of migration and interaction among tribes. The Chinese term came to adapt Amis. The Amis territory stretches from the Qilai plain to the Hengchun peninsula, where the Amis people develop an agrarian culture intricately rooted in the low lands of Taiwan’s eastern valley and coastal plains. The Amis has the largest population of aboriginals in Taiwan.There are three subcategories of the Amis people based on geographical and cultural-linguistic differences: The Northern group of “Nanshi” Amis, the Middle group of “Xiuguluan” Amis and coastal Amis, and the Southern group of “Falangaw” Amis and Hengchun Amis.The property inheritance of the Amis is matrilineal and traditional matrimony follows the rule of mikadafo which marries Amis men into the brides’ homes. The Amis tribe is co-governed by clan chiefs, who assign responsibilities and tasks to male members of different age classes. The Harvest Festival, known as Malalikid, is the most important celebration which unifies traditional beliefs, social structure and tribal identity.\n", + "tribes 300386028 The styles and cultures of various indigenous tribal populations located within the Indian subcontinent and retaining their ancient African/Austric languages, generally limited to those whose ancestral presence in the area precedes the Dravidian settlement of ca. 2000 BCE and various Aryan (Indo-European) invasions ca. 1500 BCE. In the constitution of India, in 1950 most of these groups were listed as Scheduled Tribes, targeted for social and economic development; used as the general term for the Indian scheduled tribes, who are usually descendents of these people.\n", + "tribes 300438515 Style and culture of a Native American tribe in coastal Virginia. Historically allied with the Powhatan paramountcy (but not a constituent of its confederacy) and were one of the first tribes to meet European settlers. Today the Chickahominy exist as two separate tribes with their own distinct histories, the \"Chickahominy Tribe,\" and the \"Chickahominy Tribe Eastern Division.\"\n", + "tribes 300017641 Refers to the culture of a group of three closely related Algonkian-speaking Indian tribes in Alberta and Montana, comprising the Pikuni, or Piegan, the Kainah, or Blood, and the Siksika, or Blackfoot proper (often referred to as the Northern Blackfoot). Not to be confused with the Sihasapa, another Plains Indian tribe that is also referred to as Blackfoot.\n", + "tribes 300438785 Cultures and styles of the Hla’alua people lived in Taiwan. The Hla’alua people was officially recognized as distinct from the Tsou people in 2014. As it consists of four tribes – Paiciana, Vilanganu, Hlihlala and Talicia – it used to be called by the Han Chinese as the “four-tribe huan.” Under the Japanese rule the Hla’alua people used to be perceived as a Tsou branch by the colonial official. They primarily live in Taoyuan District, Kaohsiung City. Patriarchic clans are core of the Hla’alua social organization, and their major festival is Miatungusu.\n", + "tribes 300438778 Cultures and styles of the Tsou people lived in Taiwan. The Tsou people primarily reside in Alishan Township, Chiayi County; some of them can also be found in Xinyi Township, Nantou County. The Tsou people are historically known as Cou, and they are famous for Mayasvi, a festival honoring the war god. There are two kinds of Tsou tribes, hosa and denohiyu; hosa ranks higher than denohiyu and the former possesses kuba (“main hall”) as the symbol of its power. The Tsou society is patriarchic and the basic social unit is family.\n", + "western 300021877 Describes the culture and style of the inhabitants of the Island of New Guinea whose western portion belongs to Indonesia, while the eastern half comprises part of the independent state of Papua New Guinea.\n", + "western 300263657 Refers to the culture of the region of Catalonia in western Europe, either the modern northeasterly province of Spain or the former independent principality of which the area of the modern province formed the core.\n", + "western 300017706 North American Indians of Iroquoian lineage who constituted one of the largest politically integrated tribes at the time of European colonization of the Americas. Their name is derived from a Creek word meaning 'people of different speech'; many prefer to be known as Keetoowah or Tsalagi. They formerly controlled approximately 40,000 square miles (100,000 square km) of the Appalachian Mountains in parts of present-day Georgia, eastern Tennessee, and the western parts of what are now North Carolina and South Carolina. Most members were forcibly removed from the Southeast by the U.S. government in the 1830s. Today the Cherokee Nation is a sovereign tribal government.\n", + "western 300111201 Refers to the culture of the modern nation of Norway, or in general to the cultures that have occupied the western part of the Scandinavian peninsula in northwestern Europe.\n", + "western 300417400 An art trend prevalent in Guangdong Province, China during the first half of the 20th century. Lingnan, literally meaning ‘south of the mountains,' refers to an area including Guangdong and some other southern provinces of China. The key figures of the trend were the brothers Gao Qifeng and Gao Jianfu as well as Chen Shuren. In coordination with the popular ideas of reforming China with western ‘science and democracy,' the artists aimed to create a new Chinese art that defined the nation through a synthesis of East and West. Since many artists studied in Japan, they incorporated western realism as interpreted by Japanese nihonga painting into Chinese ink painting. After the Communist revolution of 1949, the trend diminished in People’s Republic of China but further developed in Hong Kong, Taiwan and some overseas Chinese centres in Southeast Asia and North America.\n", + "western 300312337 Ancient inhabitants of Sicily in the area west of the Gelas River. According to ancient Greek writers, the Sicani were the aboriginal inhabitants of central Sicily, as distinguished from the Siculi of eastern Sicily and the Elymi of western Sicily. Archaeologically there is no substantial difference between Sicani and Siculi (Sicels) in historical times, but the Greek historian Thucydides believed the Sicani to be Iberians from Spain who were driven by the invading Siculi into the central parts of the island.\n", + "western 300262650 Style and culture of people of the modern nation of Guinée (Republic of Guinea) or of the historical people of the broader region of forest and coastal areas of western Africa between the tropic of Cancer and the equator known also as \"Guinea.\"\n", + "western 300251739 Refers to the culture of the Eastern Mono, a Native American group from central California who speak a language belonging to the Numic group of the Uto-Aztecan family and are related to Northern Paiute. The Eastern Mono, along with Owens Valley Native communities across the crest, are similar to their neighbors from the Great Basin. Historically the Eastern and Western Mono traded with one another.\n", + "western 300111207 Refers to the culture of the modern nation of Portugal, or in general to the cultures that have occupied the same area in the western part of the Iberian Peninsula.\n", + "western 300111276 Refers to the culture of the modern nation of Russia, or to the cultures that have occupied the principal lands of historic Russia in eastern Europe and northern and western Asia. It may also be used to refer to the larger group of cultures controlled by the historic Soviet Union.\n", + "white 300438466 Religious movement beginning in the 19th century based in Plateau Native North American spiritual practices. Smohalla, a Wanapum prophet and leader, developed the faith after receiving visions on how to remove white settlers from the Columbia River area. Followers believed adherence to traditional practices and peaceful opposition to colonization would revert society back to their pre-contact lifeways. The Dreamer religion continues to be observed today, with revival of Native culture and protection of the environment as major themes.\n", + "white 300262593 Carved wooden masks of the Songye people of the Democratic Republic of Congo in Africa, existing in both \"female\" and \"male\" types; the female type is used in burial rituals and the consecration of new chiefs, while the male type is used to impose discipline among the ranks of the circumcised. In form they are distinguished by prominent facial features, often including a crest, and stripes of black, red, and white. They embody attributes of the human, the animal, and the spirit.\n", + "white 300375176 A transitional visual effect used to indicate to beginning of one scene and the ending of another by means of an image gradually disappearing (fade-out), while another image grows stronger and gradually comes into view (fade-in). An image fading into black typically indicates a major separation of action, while a fade to white can indicate a character's loss of consciousness or death.\n", + "white 300249198 Social, political, and economic system of racial segregation, assigning rights to classes of people based on their racial background, supremacy being granted to those of white European extraction, with laws limiting the political participation and economic advancement of those of African, Asian, and mixed race.\n", + "white 300155665 The points of brightest reflection of light off an object; use also for the areas of brightest value in a picture, whether achieved by brightening or by leaving white areas of the support.\n", + "white 300021925 Describes the style and culture of the inhabitants of Buka Island. Changes in late 20th-century Buka art have their origins in the encounter between Pacific Islanders and the outside world. Whale hunters of the 1800s found the Buka paddles ideally suited to their work; as a result promoting the production of paddles by the Buka people. Lapita pottery and related materials have varied in style into the late 20th century. The people of Buka are known to represent human and animal forms in a naturalistic fashion, however human heads are also constructed in a canine-like style with the jaw protruded outward. Surfaces are often stained black and enhanced with inlaid patterns of red and white pigments. \n", + "white 300264340 An eclectic Islamic dervish order that originated in the 12th century with an Anatolian dervish named Hadjdji Bektash, about whom little is known. It was given definitive form in the 16th century in Anatolia (Turkey) by Bālim Sulṭān. While originally a Sufi order within Orthodox Sunnite Islam, during this period it became more syncretic and adopted tenets of the Shi'a sect. Aspects of Christianity such as confession, absolution and initiation practices were also incorporated as a result of contact with Christians. Bektashi is Shi'a in that it recognizes the twelve imāms (spiritual leaders) and venerates Ali but it is different from most other Muslim orders in that it regards traditional Islamic rituals as hypocrisy and, like many Sufi orders, is lax about observing daily Muslim laws. Bektashi allows women to take part in rituals without wearing a veil. Bektashi mystical writings are an important contribution to Sufi poetry. Through its connection with the Janissaries, an elite Ottoman military corp recruited from Christian areas, Bektashi maintained political importance from the 15th century until shortly after 1826 when the Janissaries were disbanded. The Bektashi order was dissolved in Turkey in 1925 along with all other Sufi orders but it survived in Albania until religion was banned there in 1967. It is still found in some communities in Turkey, Albanian regions of the Balkans, and the United States. Followers wear white caps with 4 or 12 folds, the 4 representing the 4 gates of Islam and the 12 representing the 12 imāms.\n", + "white 300431758 Long garments, usually white, worn by individuals performing séance rituals. Some robes also consist of a hood and face mask to cover the wearer completely. Associated with the Spiritualist movement in the United States (1850s-1890s) whose adherents believed in the presence of spirits and the ability to talk to the deceased.\n", + "white 300129784 UCL (Universal Color Language) standard color name identifying whitish colors, such as the color of snow or milk. More specifically, white is the absence of color. It is the color produced by reflection, transmission, or emission of all kinds of light in the proportion in which they exist in the complete visible spectrum, without sensible absorption, being thus fully luminous and devoid of any distinctive hue.\n", + "white 300312263 The process of forming a whole from various parts, particularly the formation of a compound material by the combination of its elements or constituents, of the production of white or other compound light by the combination of its constituent colors, or of the production of a complex musical sound by the combination of its component simple tones. In philosophy, it is the action of proceeding in thought from causes to effects, or from laws or principles to their consequences.\n" + ] + } + ], + "source": [ + "case_3 = []\n", + "case_3_count = 0\n", + "for term, hits in aat_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"scopeNote\":\n", + " case_3_count += 1\n", + " case_3.append(hit[\"aat_uri\"])\n", + " print(term, hit[\"aat_uri\"], hit[\"scopeNote\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "342" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_3_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open(f\"selected_cases/aat_{lang}_case3.txt\",'w') as txt_file:\n", + " for l in case_3:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## PWN" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [], + "source": [ + "# import subset\n", + "with open(\"/Users/anesterov/reps/LODlit/PWN/pwn_subset.json\",'r') as jf:\n", + " pwn_subset = json.load(jf)" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [], + "source": [ + "# AAT EN entities with implicit markers\n", + "pwn_implicit = implicit_markers[implicit_markers[\"resource\"] == \"pwn\"][\"entity_id\"].to_list()\n", + "\n", + "# AAT EN entities with explicit markers\n", + "pwn_explicit = explicit_markers[explicit_markers[\"resource\"] == \"aat\"][\"entity_id\"].to_list()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 4" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal aboriginal.s.02 having existed from the beginning; in an earliest or original stage or state ['aboriginal forests', 'primal eras before the appearance of life on earth', 'the forest primeval', 'primordial matter', 'primordial forms of life']\n", + "aboriginal native.a.03 characteristic of or relating to people inhabiting a region from the beginning ['native Americans', 'the aboriginal peoples of Australia']\n", + "aboriginal australia.n.01 a nation occupying the whole of the Australian continent; Aboriginal tribes are thought to have migrated from southeastern Asia 20,000 years ago; first Europeans were British convicts sent there as a penal colony []\n", + "aboriginal native.n.01 an indigenous person who was born in a particular place ['the art of the natives of the northwest coast', 'the Canadian government scrapped plans to tax the grants to aboriginal college students']\n", + "aboriginal dravidian.n.01 a member of one of the aboriginal inhabitants of India []\n", + "aboriginal alaska_native.n.01 a member or descendant of any of the aboriginal peoples of Alaska []\n", + "barbarian barbarian.s.01 without civilizing influences; ; ; ; -Margaret Meade ['barbarian invaders', 'barbaric practices', 'a savage people', 'fighting is crude and uncivilized especially if the weapons are efficient', 'wild tribes']\n", + "barbarian attila.n.01 king of the Huns; the most successful barbarian invader of the Roman Empire (406-453) []\n", + "barbarian odoacer.n.01 Germanic barbarian leader who ended the Western Roman Empire in 476 and became the first barbarian ruler of Italy (434-493) []\n", + "barbarians sack.v.01 plunder (a town) after capture ['the barbarians sacked Rome']\n", + "berber tuareg.n.02 the dialect of Berber spoken by the Tuareg []\n", + "berber almoravid.n.01 a member of a Muslim dynasty of Berber warriors that flourished from 1049 to 1145 and that established political dominance over northwestern Africa and Spain []\n", + "berber moor.n.01 one of the Muslim people of north Africa; of mixed Arab and Berber descent; converted to Islam in the 8th century; conqueror of Spain in the 8th century []\n", + "berber tuareg.n.01 a member of a nomadic Berber people of the Sahara []\n", + "berber riff.n.01 a Berber living in northern Morocco []\n", + "berbers berbers.n.01 an ethnic minority descended from Berbers and Arabs and living in northern Africa []\n", + "black black.a.02 of or belonging to a racial group especially of sub-Saharan African origin; - Martin Luther King Jr. ['a great people--a black people--...injected new meaning and dignity into the veins of civilization']\n", + "black bordered.a.01 having a border especially of a specified kind; sometimes used as a combining term ['black-bordered handkerchief']\n", + "black black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "black black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "black black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "black field_cricket.n.01 common American black cricket; attacks crops and also enters dwellings []\n", + "black negritude.n.01 an ideological position that holds Black culture to be independent and valid on its own terms; an affirmation of the African cultural heritage []\n", + "black gospel.n.03 folk music consisting of a genre of a cappella music originating with Black slaves in the United States and featuring call and response; influential on the development of other genres of popular music (especially soul) []\n", + "black soul.n.05 a secular form of gospel that was a major Black musical genre in the 1960s and 1970s ['soul was politically significant during the Civil Rights movement']\n", + "black ku_klux_klan.n.01 a secret society of white Southerners in the United States; was formed in the 19th century to resist the emancipation of slaves; used terrorist tactics to suppress Black people []\n", + "black abkhaz.n.02 an autonomous province of Georgia on the Black Sea; a strong independence movement has resulted in much instability []\n", + "bombay gujarat.n.01 an industrialized state in western India that includes parts of Bombay []\n", + "bombay farsi.n.01 a person of Iranian descent ['many Farsi emigrated to India near Bombay']\n", + "burma yellow-throated_marten.n.01 large yellow and black marten of southern China and Burma []\n", + "burma kamarupan.n.01 the Tibeto-Burman language spoken in northeastern India and adjacent regions of western Burma []\n", + "burma loloish.n.01 languages spoken by hill tribes in northern Burma and neighboring areas []\n", + "burma kachin.n.01 Tibeto-Burman languages spoken in northernmost Burma and adjacent China and India []\n", + "burma kuki.n.01 Kamarupan languages spoken in western Burma and Bangladesh and easternmost India []\n", + "burma naga.n.01 Kamarupan languages spoken in northeastern India and western Burma []\n", + "burma irrawaddy.n.01 the main river of Myanmar rising in the north and flowing south through the length of Burma to empty into the Andaman Sea []\n", + "burma stilwell.n.01 United States general who commanded the Allied forces in China and Burma and India during World War II (1883-1946) []\n", + "burma pepper.n.01 climber having dark red berries (peppercorns) when fully ripe; southern India and Sri Lanka; naturalized in northern Burma and Assam []\n", + "calcutta calcuttan.a.01 of or relating to or characteristic of Calcutta or its inhabitants []\n", + "calcutta black_hole_of_calcutta.n.01 a dungeon (20 feet square) in a fort in Calcutta where as many as 146 English prisoners were held overnight by Siraj-ud-daula; the next morning only 23 were still alive []\n", + "calcutta mumbai.n.01 a city in western India just off the coast of the Arabian Sea; India's 2nd largest city (after Calcutta); has the only natural deep-water harbor in western India []\n", + "calcutta siraj-ud-daula.n.01 Indian general and nawab of Bengal who opposed the colonization of India by England; he captured Calcutta in 1756 and many of his prisoners suffocated in a crowded room that became known as the Black Hole of Calcutta; he was defeated at the battle of Plassey by a group of Indian nobles in alliance with Robert Clive (1728-1757) []\n", + "calcutta originate.v.03 begin a trip at a certain point, as of a plane, train, bus, etc. ['The flight originates in Calcutta']\n", + "caucasian caucasian.s.02 of or relating to Caucasian people []\n", + "caucasian caucasian.a.01 of or relating to the geographical region of Caucasia ['Caucasian languages']\n", + "caucasian chechen.n.02 a northern Caucasian language spoken by the Chechen []\n", + "caucasian circassian.n.03 a northern Caucasian language spoken by the Circassian []\n", + "caucasian georgian.n.03 a southern Caucasian language with 3 million speakers and a long literary tradition []\n", + "caucasian ubykh.n.01 an extinct Caucasian language spoken exclusively in Turkey []\n", + "caucasian aryan.n.01 (according to Nazi doctrine) a Caucasian person of Nordic descent (and not a Jew) []\n", + "caucasian half-breed.n.01 an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry) []\n", + "caucasian metis.n.01 a person in western Canada who is of Caucasian and American Indian ancestry []\n", + "colored colored.a.01 having color or a certain color; sometimes used in combination ['colored crepe paper', 'the film was in color', 'amber-colored heads of grain']\n", + "colored colored.a.01 having color or a certain color; sometimes used in combination ['colored crepe paper', 'the film was in color', 'amber-colored heads of grain']\n", + "colored light.a.02 (used of color) having a relatively small amount of coloring agent ['light blue', 'light colors such as pastels', 'a light-colored powder']\n", + "colored thimerosal.n.01 a light-colored crystalline powder (trade name Merthiolate) used as a surgical antiseptic []\n", + "colored granny's_bonnets.n.01 common European columbine having variously colored (white or blue to purple or red) short-spurred flowers; naturalized in United States []\n", + "colored moniliaceae.n.01 family of imperfect fungi having white or brightly colored hyphae and spores that are produced directly on the mycelium and not aggregated in fruiting bodies []\n", + "colored earth_color.n.01 a colored mineral used as a pigment []\n", + "colored sardonyx.n.01 an onyx characterized by parallel layers of sard and a different colored mineral []\n", + "colored toner.n.02 a black or colored powder used in a printer to develop a xerographic image []\n", + "descent ancestral.s.01 inherited or inheritable by established rules (usually legal rules) of descent ['ancestral home', 'ancestral lore', 'hereditary monarchy', 'patrimonial estate', 'transmissible tradition']\n", + "descent lineal.a.01 in a straight unbroken line of descent from parent to child ['lineal ancestors', 'lineal heirs', 'a direct descendant of the king', 'direct heredity']\n", + "descent unilateral.s.02 tracing descent from either the paternal or the maternal line only []\n", + "descent relative.n.02 an animal or plant that bears a relationship to another (as related by common descent or by membership in the same genus) []\n", + "descent generation.n.02 group of genetically related organisms constituting a single step in the line of descent []\n", + "descent jew.n.01 a person belonging to the worldwide group claiming descent from Jacob (or converted to it) and connected by cultural or religious ties []\n", + "descent tay-sachs_disease.n.01 a hereditary disorder of lipid metabolism occurring most frequently in individuals of Jewish descent in eastern Europe; accumulation of lipids in nervous tissue results in death in early childhood []\n", + "developing nations external.s.03 from or between other countries ['external commerce', 'international trade', 'developing nations need outside help']\n", + "developing nations international_bank_for_reconstruction_and_development.n.01 a United Nations agency created to assist developing nations by loans guaranteed by member governments []\n", + "disabled permanently.r.01 for a long time without essential change ['he is permanently disabled']\n", + "disabled physical_rehabilitation.n.01 providing help for disabled persons; the removal or reduction of disabilities []\n", + "disabled personal_care.n.01 care for someone who is disabled or is otherwise unable to care for themselves; can including bathing and cooking and managing bodily functions []\n", + "disabled disability_insurance.n.01 social insurance for the disabled []\n", + "disabled sheltered_workshop.n.01 a workshop that offers jobs to members of the physically or developmentally disabled population []\n", + "disabled living_will.n.01 a document written by someone still legally capable requesting that he should be allowed to die if subsequently severely disabled or suffering terminal illness ['after he discovered he had AIDS he drew up a living will']\n", + "disabled disabled.n.01 people collectively who are crippled or otherwise physically handicapped ['technology to help the elderly and the disabled']\n", + "disabled disability_check.n.01 a monthly payment made to someone who has become disabled and is unable to work []\n", + "disabled disable.v.02 injure permanently ['He was disabled in a car accident']\n", + "discover ascertain.v.04 learn or discover with certainty []\n", + "discover discover.v.04 make a discovery ['She found that he had lied to her', 'The story is false, so far as I can discover']\n", + "discover trace.v.01 follow, discover, or ascertain the course of development of something ['We must follow closely the economic development is Cuba', \"trace the student's progress\", \"trace one's ancestry\"]\n", + "discover detect.v.01 discover or determine the existence, presence, or fact of ['She detected high levels of lead in her drinking water', 'We found traces of lead in the paint']\n", + "discover locate.v.01 discover the location of; determine the place of; find by searching or examining ['Can you locate your cousins in the Midwest?', 'My search turned up nothing']\n", + "dwarf dwarfish.s.01 atypically small ['dwarf tree', 'dwarf star']\n", + "dwarf dwarfish.s.01 atypically small ['dwarf tree', 'dwarf star']\n", + "dwarf microcephalic.a.01 having an abnormally small head and underdeveloped brain ['a nanocephalic dwarf']\n", + "dwarf troll.n.01 (Scandanavian folklore) a supernatural creature (either a dwarf or a giant) that is supposed to live in caves or in the mountains []\n", + "dwarf pituitary_dwarf.n.01 a dwarf whose condition is caused by a deficiency of growth hormones, rather than by genetic factors (as in the case of the achondroplastic dwarf) []\n", + "dwarf primordial_dwarf.n.01 an achondroplastic dwarf whose small size is the result of a genetic defect; body parts and mental and sexual development are normal []\n", + "dwarf dryadella.n.01 comprises tropical American species usually placed in genus Masdevallia: very dwarf plants having short tufted and usually unifoliate stems with usually solitary flowers []\n", + "dwarf one-flowered_wintergreen.n.01 delicate evergreen dwarf herb of north temperate regions having a solitary white terminal flower; sometimes placed in genus Pyrola []\n", + "dwarf wild_thyme.n.01 aromatic dwarf shrub common on banks and hillsides in Europe; naturalized in United States []\n", + "eskimo tupik.n.01 tent that is an Eskimo summer dwelling []\n", + "eskimo eskimo-aleut.n.01 the family of languages that includes Eskimo and Aleut []\n", + "eskimo eskimo.n.02 the language spoken by the Eskimo []\n", + "eskimo aleut.n.02 a community of Native Americans who speak an Eskimo-Aleut language and inhabit the Aleutian Islands and southwestern Alaska ['the Aleut and the Eskimo are related culturally and linguistically']\n", + "eskimo aleut.n.02 a community of Native Americans who speak an Eskimo-Aleut language and inhabit the Aleutian Islands and southwestern Alaska ['the Aleut and the Eskimo are related culturally and linguistically']\n", + "eskimo lake_clark_national_park.n.01 a national park in Alaska having Eskimo and Athapaskan archeological sites []\n", + "eskimo eskimo.n.01 a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people') []\n", + "eskimos syllabic.a.02 consisting of or using a syllabary ['eskimos of the eastern Arctic have a system of syllabic writing']\n", + "eskimos kayak.n.01 a small canoe consisting of a light frame made watertight with animal skins; used by Eskimos []\n", + "eskimos rasmussen.n.01 Danish ethnologist and Arctic explorer; led expeditions into the Arctic to find support for his theory that Eskimos and North American Indians originally migrated from Asia (1879-1933) []\n", + "ethnic group ethnocentric.a.01 centered on a specific ethnic group, usually one's own []\n", + "ethnic group pogrom.n.01 organized persecution of an ethnic group (especially Jews) []\n", + "ethnic group communalism.n.02 loyalty and commitment to the interests of your own minority or ethnic group rather than to society as a whole []\n", + "ethnic group ethnocentrism.n.01 belief in the superiority of one's own ethnic group []\n", + "ethnic group peoples.n.01 the human beings of a particular nation or community or ethnic group ['the indigenous peoples of Australia']\n", + "ethnic group ghetto.n.03 a poor densely populated city district occupied by a minority ethnic group linked together by economic hardship and social restrictions []\n", + "ethnic group pathan.n.01 a member of the mountain people living in the eastern regions of Afghanistan ['Pathans are the predominant ethnic group in Afghanistan']\n", + "ethnic group kurd.n.01 a member of a largely pastoral Islamic people who live in Kurdistan; the largest ethnic group without their own state []\n", + "ethnic groups multiethnic.s.01 involving several ethnic groups []\n", + "ethnic groups desegregate.v.01 open (a place) to members of all races and ethnic groups ['This school is completely desegregated']\n", + "ethnicity ethnically.r.01 with respect to ethnicity ['the neighborhood is ethnically diverse']\n", + "ethnicity ethnicity.n.01 an ethnic quality or affiliation resulting from racial or cultural ties ['ethnicity has a strong influence on community status relations']\n", + "exotic exotic.s.02 strikingly strange or unusual ['an exotic hair style', 'protons, neutrons, electrons and all their exotic variants', 'the exotic landscape of a dead planet']\n", + "exotic exotic.s.02 strikingly strange or unusual ['an exotic hair style', 'protons, neutrons, electrons and all their exotic variants', 'the exotic landscape of a dead planet']\n", + "exotic exotic.s.02 strikingly strange or unusual ['an exotic hair style', 'protons, neutrons, electrons and all their exotic variants', 'the exotic landscape of a dead planet']\n", + "exotic alien.s.02 being or from or characteristic of another place or part of the world ['alien customs', 'exotic plants in a greenhouse', 'exotic cuisine']\n", + "exotic alien.s.02 being or from or characteristic of another place or part of the world ['alien customs', 'exotic plants in a greenhouse', 'exotic cuisine']\n", + "exotic ecotourism.n.01 tourism to exotic or threatened ecosystems to observe wildlife or to help preserve nature []\n", + "exotic pasty.n.02 (usually used in the plural) one of a pair of adhesive patches worn to cover the nipples of exotic dancers and striptease performers []\n", + "exotic exoticism.n.01 the quality of being exotic ['he loved the exoticism of Egypt']\n", + "exotic biosafety_level_4.n.01 exposure to exotic infectious agents that pose a high risk of life-threatening disease and can be transmitted as an aerosol and for which there is no vaccine or therapy []\n", + "exotic erupt.v.07 appear on the skin ['A rash erupted on her arms after she had touched the exotic plant']\n", + "exotic romance.v.04 tell romantic or exaggerated lies ['This author romanced his trip to an exotic country']\n", + "exotic introduce.v.05 bring in or establish in a new place or environment ['introduce a rule', 'introduce exotic fruits']\n", + "first world armageddon.n.02 any catastrophically destructive battle ['they called the first World War an Armageddon']\n", + "first world commemorate.v.02 call to remembrance; keep alive the memory of someone or something, as in a ceremony ['We remembered the 50th anniversary of the liberation of Auschwitz', 'Remember the dead of the First World War']\n", + "footman lackey.n.01 a male servant (especially a footman) []\n", + "footmen liveried.a.01 wearing livery ['liveried footmen stood on the palace steps']\n", + "gay bright.s.09 characterized by happiness or gladness ['bright faces', 'all the world seems bright and gay']\n", + "gay gay.s.03 given to social pleasures often including dissipation ['led a gay Bohemian life', 'a gay old rogue with an eye for the ladies']\n", + "gay gay.s.03 given to social pleasures often including dissipation ['led a gay Bohemian life', 'a gay old rogue with an eye for the ladies']\n", + "gay gaily.r.01 in a gay manner ['the scandals were gaily diverting']\n", + "gay antonym.n.01 a word that expresses a meaning opposed to the meaning of another word, in which case the two words are antonyms of each other [\"to him the antonym of `gay' was `depressed'\"]\n", + "gay gaiety.n.01 a gay feeling []\n", + "gay ghetto.n.02 any segregated mode of living or working that results from bias or stereotyping ['the relative security of the gay ghetto', 'no escape from the ghetto of the typing pool']\n", + "gay out.v.02 reveal (something) about somebody's identity or lifestyle ['The gay actor was outed last week', 'Someone outed a CIA agent']\n", + "gay excommunicate.v.01 exclude from a church or a religious community ['The gay priest was excommunicated when he married his partner']\n", + "gypsies romany.a.01 of or relating to the Gypsies or their language or culture ['Romani nomads', 'Romany folk songs', 'a Gypsy fortune-teller']\n", + "gypsies flamenco.n.02 a style of dancing characteristic of the Andalusian Gypsies; vigorous and rhythmic with clapping and stamping of feet []\n", + "gypsies romany.n.02 the Indic language of the Gypsies []\n", + "gypsies exterminate.v.01 kill en masse; kill on a large scale; kill many ['Hitler wanted to exterminate the Jews, Gypsies, Communists, and homosexuals of Europe']\n", + "gypsies roll.v.12 move about aimlessly or without any destination, often in search of food or employment ['The gypsies roamed the woods', 'roving vagabonds', 'the wandering Jew', 'The cattle roam across the prairie', 'the laborers drift from one town to the next', 'They rolled from town to town']\n", + "gypsies chiromance.v.01 divine by reading someone's palms ['The Gypsies chiromanced', 'She refused to chiromance my fate']\n", + "gypsy gypsy.n.03 a person who resembles a Gypsy in leading an unconventional, nomadic way of life []\n", + "gypsy tinker.n.02 formerly a person (traditionally a Gypsy) who traveled from place to place mending pots and kettles and other metal utensils as a way to earn a living []\n", + "handicap penalty.n.04 (games) a handicap or disadvantage that is imposed on a competitor (or a team) for an infraction of the rules of the game []\n", + "handicap welterweight.n.01 a weight of 28 pounds; sometimes imposed as a handicap in a horse race (such as a steeplechase) []\n", + "handicap succeed.v.01 attain success or reach a desired goal ['The enterprise succeeded', 'We succeeded in getting tickets to the show', 'she struggled to overcome her handicap and won']\n", + "handicaps albatross.n.01 (figurative) something that hinders or handicaps ['she was an albatross around his neck']\n", + "hermaphrodite pseudohermaphrodite.n.01 someone having external genitalia of one sex and internal sex organs of the other sex; not a true hermaphrodite because there is no ambiguity in the sex of the external genitalia and hence no question about gender at birth []\n", + "homo sapiens.a.01 of or relating to or characteristic of Homo sapiens []\n", + "homo pithecanthropus.n.01 former genus of primitive apelike men now Homo erectus []\n", + "homo javanthropus.n.01 former genus of primitive man; now Homo soloensis: comprises Solo man []\n", + "homo language.n.05 the mental faculty or power of vocal communication ['language sets homo sapiens apart from all other animals']\n", + "homosexual homophobic.s.01 prejudiced against homosexual people []\n", + "homosexual gay.s.06 homosexual or arousing homosexual desires []\n", + "homosexual lesbian.s.01 of or relating to or characterized by homosexual relations between woman []\n", + "homosexual tribadistic.a.01 of female homosexual behavior that attempts to simulate heterosexual behavior []\n", + "homosexual heterosexism.n.01 discrimination in favor of heterosexual and against homosexual people []\n", + "homosexual beard.n.03 a person who diverts suspicion from someone (especially a woman who accompanies a male homosexual in order to conceal his homosexuality) []\n", + "homosexual closet_queen.n.01 a negative term for a homosexual man who chooses not to reveal his sexual orientation []\n", + "homosexuals butch.s.02 (of male or female homosexuals) characterized by stereotypically male traits or appearance []\n", + "immigrant old_country.n.01 the country of origin of an immigrant []\n", + "immigrants ethiopian.a.01 of or relating to or characteristic of Ethiopia or its people or languages ['Ethiopian immigrants']\n", + "immigrants nationality.n.01 people having common origins or traditions and often comprising a nation ['immigrants of the same nationality often seek each other out', 'such images define their sense of nationality']\n", + "immigrants immigration.n.02 the body of immigrants arriving during a specified interval ['the increased immigration strengthened the colony']\n", + "immigrants coyote.n.02 someone who smuggles illegal immigrants into the United States (usually across the Mexican border) []\n", + "immigrants assimilate.v.03 make similar ['This country assimilates immigrants very quickly']\n", + "immigrants immigrate.v.02 introduce or send as immigrants ['Britain immigrated many colonists to America']\n", + "immigrants settle.v.04 take up residence and become established ['The immigrants settled in the Midwest']\n", + "immigrants restrain.v.01 to close within bounds, or otherwise limit or deprive of free movement ['This holds the local until the express passengers change trains', 'About a dozen animals were held inside the stockade', 'The illegal immigrants were held at a detention center', 'The terrorists held the journalists for ransom']\n", + "indian indian.a.02 of or pertaining to Native Americans or their culture or languages ['Native American religions', 'Indian arrowheads']\n", + "indian indian.a.01 of or relating to or characteristic of India or the East Indies or their peoples or languages or cultures ['the Indian subcontinent', 'Indian saris']\n", + "indian indian.a.01 of or relating to or characteristic of India or the East Indies or their peoples or languages or cultures ['the Indian subcontinent', 'Indian saris']\n", + "indian brahman.n.04 any of several breeds of Indian cattle; especially a large American heat and tick resistant greyish humped breed evolved in the Gulf States by interbreeding Indian cattle and now used chiefly for crossbreeding []\n", + "indian athapaskan.n.01 a member of any of the North American Indian groups speaking an Athapaskan language and living in the subarctic regions of western Canada and central Alaska []\n", + "indian mayan.n.01 a member of an American Indian people of Yucatan and Belize and Guatemala who had a culture (which reached its peak between AD 300 and 900) characterized by outstanding architecture and pottery and astronomy ['Mayans had a system of writing and an accurate calendar']\n", + "indian chinook.n.02 a member of an important North American Indian people who controlled the mouth of the Columbia river; they were organized into settlements rather than tribes []\n", + "indian shoshone.n.01 a member of the North American Indian people (related to the Aztecs) of the southwestern United States []\n", + "indian half-breed.n.01 an offensive term for an offspring of parents of different racial group (especially of Caucasian and American Indian ancestry) []\n", + "indian jat.n.01 a member of an Indo-European people widely scattered throughout the northwest of the Indian subcontinent and consisting of Muslims and Hindus and Sikhs []\n", + "indians wickiup.n.01 a lodge consisting of a frame covered with matting or brush; used by nomadic American Indians in the southwestern United States []\n", + "indigenous autochthonal.s.01 originating where it is found ['the autochthonal fauna of Australia includes the kangaroo', 'autochthonous rocks and people and folktales', 'endemic folkways', 'the Ainu are indigenous to the northernmost islands of Japan']\n", + "indigenous substrate.n.04 an indigenous language that contributes features to the language of an invading people who impose their language on the indigenous population ['the Celtic languages of Britain are a substrate for English']\n", + "indigenous superstrate.n.02 the language of a later invading people that is imposed on an indigenous population and contributes features to their language []\n", + "indigenous chukchi.n.02 an indigenous and isolated language of unknown origin spoken by the Chukchi that is pronounced differently by men and women []\n", + "indigenous ural-altaic.n.01 a (postulated) group of languages including many of the indigenous languages of Russia (but not Russian) []\n", + "indigenous finno-ugric.n.01 a family of Uralic languages indigenous to Scandinavia and Hungary and Russia and western Siberia (prior to the Slavic expansion into those regions) []\n", + "indigenous peoples.n.01 the human beings of a particular nation or community or ethnic group ['the indigenous peoples of Australia']\n", + "indigenous lapp.n.01 a member of an indigenous nomadic people living in northern Scandinavia and herding reindeer []\n", + "indigenous native_hawaiian.n.01 a member or descendant of the indigenous Polynesian people who lived in the Hawaiian Islands []\n", + "indigenous chukchi.n.01 a member of an indigenous people living on the Chukchi Peninsula []\n", + "indo indo-european.a.01 of or relating to the Indo-European language family []\n", + "indo armenian.n.02 the Indo-European language spoken predominantly in Armenia, but also in Azerbaijan []\n", + "indo thraco-phrygian.n.01 an extinct branch of the Indo-European language family thought by some to be related to Armenian []\n", + "indo balto-slavic.n.01 a family of Indo-European languages including the Slavic and Baltic languages []\n", + "indo baltic.n.02 a branch of the Indo-European family of languages related to the Slavonic languages; Baltic languages have preserved many archaic features that are believed to have existed in Proto-Indo European []\n", + "indo germanic.n.01 a branch of the Indo-European family of languages; members that are spoken currently fall into two major groups: Scandinavian and West Germanic []\n", + "indo english.n.01 an Indo-European language belonging to the West Germanic branch; the official language of Britain and the United States and most of the commonwealth countries []\n", + "indo tocharian.n.01 a branch of the Indo-European language family that originated in central Asia during the first millennium A.D. []\n", + "indo anatolian.n.01 an extinct branch of the Indo-European family of languages known from inscriptions and important in the reconstruction of Proto-Indo European []\n", + "indo jat.n.01 a member of an Indo-European people widely scattered throughout the northwest of the Indian subcontinent and consisting of Muslims and Hindus and Sikhs []\n", + "inuit nunavut.n.01 an Arctic territory in northern Canada created in 1999 and governed solely by the Inuit; includes the eastern part of what was the Northwest Territories and most of the islands of the Arctic Archipelago ['Nunavut is the homeland of the Inuit people']\n", + "inuit nunavut.n.01 an Arctic territory in northern Canada created in 1999 and governed solely by the Inuit; includes the eastern part of what was the Northwest Territories and most of the islands of the Arctic Archipelago ['Nunavut is the homeland of the Inuit people']\n", + "inuit eskimo.n.01 a member of a people inhabiting the Arctic (northern Canada or Greenland or Alaska or eastern Siberia); the Algonquians called them Eskimo (`eaters of raw flesh') but they call themselves the Inuit (`the people') []\n", + "lilliputian fiddling.s.01 (informal) small and of little importance ['a fiddling sum of money', 'a footling gesture', 'our worries are lilliputian compared with those of countries that are at war', 'a little (or small) matter', 'a dispute over niggling details', 'limited to petty enterprises', 'piffling efforts', 'giving a police officer a free meal may be against the law, but it seems to be a picayune infraction']\n", + "lilliputian bantam.s.01 very small ['diminutive in stature', 'a lilliputian chest of drawers', 'her petite figure', 'tiny feet', 'the flyspeck nation of Bahrain moved toward democracy']\n", + "lilliputian lilliputian.a.01 tiny; relating to or characteristic of the imaginary country of Lilliput ['the Lilliputian population']\n", + "lilliputian lilliputian.n.01 a very small person (resembling a Lilliputian) []\n", + "madras savara.n.02 a Dravidian language spoken by the Savara in southeastern India (north of Madras) []\n", + "madras chennai.n.01 a city in Tamil Nadu on the Bay of Bengal; formerly Madras []\n", + "madras tamil_nadu.n.01 a state in southeastern India on the Bay of Bengal (south of Andhra Pradesh); formerly Madras []\n", + "maroon ketembilla.n.02 maroon-purple gooseberry-like fruit of India having tart-sweet purple pulp used especially for preserves []\n", + "maroon maroon.n.01 a person who is stranded (as on an island) ['when the tide came in I was a maroon out there']\n", + "maroon leopard_lily.n.01 lily of western United States having orange-red to crimson maroon-spotted flowers []\n", + "maroon snake's_head_fritillary.n.01 Eurasian checkered lily with pendant flowers usually veined and checkered with purple or maroon on a pale ground and shaped like the bells carried by lepers in medieval times; widely grown as an ornamental []\n", + "maroon hog_peanut.n.01 vine widely distributed in eastern North America producing racemes of purple to maroon flowers and abundant (usually subterranean) edible one-seeded pods resembling peanuts []\n", + "maroon hyacinth_bean.n.01 perennial twining vine of Old World tropics having trifoliate leaves and racemes of fragrant purple pea-like flowers followed by maroon pods of edible seeds; grown as an ornamental and as a vegetable on the Indian subcontinent; sometimes placed in genus Dolichos []\n", + "medicine man rainmaker.n.02 American Indian medicine man who attempt to make it rain []\n", + "mestizos criollo.n.01 a Spanish American of pure European stock (usually Spanish) ['Mexico is a country of mestizos, criollos, and indigenes']\n", + "mongoloid mongoloid.a.01 characteristic of or resembling a Mongol ['the mongoloid epicanthic fold']\n", + "mongoloid mongoloid.n.01 a member of the Mongoloid family []\n", + "moor marston_moor.n.01 a former moor in northern England []\n", + "moor converso.n.01 (medieval Spain and Portugal) a Jew or Moor who professed to convert to Christianity in order to avoid persecution or expulsion []\n", + "moors moorish.a.01 relating to or characteristic of the Moors ['Moorish courtyard']\n", + "moors alcazar.n.01 any of various Spanish fortresses or palaces built by the Moors []\n", + "moors granada.n.01 a city in southeastern Spain that was the capital of the Moorish kingdom until it was captured by Ferdinand and Isabella in 1492; site of the Alhambra (a palace and fortress built by Moors in the Middle Ages) which is now a major tourist attraction []\n", + "moors ferdinand.n.01 the king of Castile and Aragon who ruled jointly with his wife Isabella; his marriage to Isabella I in 1469 marked the beginning of the modern state of Spain and their capture of Granada from the Moors in 1492 united Spain as one country; they instituted the Spanish Inquisition in 1478 and supported the expedition of Christopher Columbus in 1492 (1452-1516) []\n", + "moors cornish_heath.n.01 bushy shrub having pink to white flowers; common on the moors of Cornwall and in southwestern Europe; cultivated elsewhere []\n", + "moors broom_tree.n.01 prickly yellow-flowered shrub of the moors of New England and Europe []\n", + "mulatto quadroon.n.01 an offspring of a mulatto and a white parent; a person who is one-quarter black []\n", + "native native.a.01 characteristic of or existing by virtue of geographic origin ['the native North American sugar maple', 'many native artists studied abroad']\n", + "native native.a.01 characteristic of or existing by virtue of geographic origin ['the native North American sugar maple', 'many native artists studied abroad']\n", + "native native.a.03 characteristic of or relating to people inhabiting a region from the beginning ['native Americans', 'the aboriginal peoples of Australia']\n", + "native endemic.a.02 native to or confined to a certain region ['the islands have a number of interesting endemic species']\n", + "native emigration.n.01 migration from a place (especially migration from your native country in order to settle in another) []\n", + "native asian_tiger_mosquito.n.01 striped native of Japan thriving in southwestern and midwestern United States and spreading to the Caribbean; potential carrier of serious diseases []\n", + "native aleut.n.02 a community of Native Americans who speak an Eskimo-Aleut language and inhabit the Aleutian Islands and southwestern Alaska ['the Aleut and the Eskimo are related culturally and linguistically']\n", + "native brinton.n.01 United States anthropologist who was the first to attempt a systematic classification of Native American languages (1837-1899) []\n", + "native whitman.n.02 United States frontier missionary who established a post in Oregon where Christianity and schooling and medicine were available to Native Americans (1802-1847) []\n", + "native fox_grape.n.01 native grape of northeastern United States; origin of many cultivated varieties e.g. Concord grapes []\n", + "natives native.n.01 an indigenous person who was born in a particular place ['the art of the natives of the northwest coast', 'the Canadian government scrapped plans to tax the grants to aboriginal college students']\n", + "negro blackface.n.01 the makeup (usually burnt cork) used by a performer in order to imitate a Negro []\n", + "negro minstrel_show.n.01 a troupe of performers in blackface typically giving a comic program of negro songs and jokes []\n", + "negro liberia.n.01 a republic in West Africa; established in 1822 by Americans as a way to free negro slaves []\n", + "negro black.n.05 a person with African ancestry, and are archaic and pejorative today ['Negro', 'Negroid']\n", + "negroes white.s.05 restricted to whites only ['under segregation there were even white restrooms and white drinking fountains', 'a lily-white movement which would expel Negroes from the organization']\n", + "oriental western.a.01 relating to or characteristic of the western parts of the world or the West as opposed to the eastern or oriental parts ['the western world', 'western thought']\n", + "oriental oriental.s.01 denoting or characteristic of countries of the Far East ['oriental civilization']\n", + "oriental incidentally.r.02 of a minor or subordinate nature ['these magnificent achievements were only incidentally influenced by Oriental models']\n", + "oriental martial_art.n.01 any of several Oriental arts of weaponless self-defense; usually practiced as a sport ['he had a black belt in the martial arts']\n", + "oriental selvage.n.01 border consisting of an ornamental fringe at either end of an oriental carpet []\n", + "oriental fluidity.n.02 a changeable quality ['a charming Oriental fluidity of manner', 'a certain fluidness in his perception of time made him an unpredictable colleague', 'demographers try to predict social fluidity']\n", + "oriental neoplatonism.n.01 a system of philosophical and theological doctrines composed of elements of Platonism and Aristotelianism and oriental mysticism; its most distinctive doctrine holds that the first principle and source of reality transcends being and thought and is naturally unknowable ['Neoplatonism was predominant in pagan Europe until the 6th century', 'Neoplatonism was a major influence on early Christian writers and on later medieval and Renaissance thought and on Islamic philosophy']\n", + "oriental orientalist.n.01 a specialist in oriental subjects []\n", + "oriental tobey.n.01 United States abstract painter influenced by oriental calligraphy (1890-1976) []\n", + "oriental armillaria_ponderosa.n.01 a large white mushroom that develops brown stains as it ages; gills are white; odor is spicy and aromatic; collected commercially for oriental cooking the Pacific Northwest []\n", + "page social.a.03 relating to or belonging to or characteristic of high society ['made fun of her being so social and high-toned', 'a social gossip colum', 'the society page']\n", + "page example.n.01 an item of information that is typical of a class or group ['this patient provides a typical example of the syndrome', 'there is an example on page 10']\n", + "page playbook.n.03 a scheme or set of strategies for conducting a business campaign or a political campaign ['they borrowed a page from the playbook of the opposition']\n", + "page opinion.n.02 a message expressing a belief about something; the expression of a belief that is held with confidence but not substantiated by positive knowledge or proof ['his opinions appeared frequently on the editorial page']\n", + "pages disorganized.a.01 lacking order or methodical arrangement or function ['a disorganized enterprise', 'a thousand pages of muddy and disorganized prose', 'she was too disorganized to be an agreeable roommate']\n", + "pages absurd.s.02 so unreasonable as to invite derision ['the absurd excuse that the dog ate his homework', \"that's a cockeyed idea\", 'ask a nonsensical question and get a nonsensical answer', 'a contribution so small as to be laughable', 'it is ludicrous to call a cottage a mansion', 'a preposterous attempt to turn back the pages of history', 'her conceited assumption of universal interest in her rather dull children was ridiculous']\n", + "pages family_bible.n.01 a large Bible with pages to record marriages and births []\n", + "pages belong_to.v.01 be a part or adjunct ['the uniform looks like it belonged to a museum collection', \"These pages don't belong\"]\n", + "primitive appellative.s.02 inclined to or serving for the giving of names ['the appellative faculty of children', 'the appellative function of some primitive rites']\n", + "primitive crude.s.04 belonging to an early stage of technical development; characterized by simplicity and (often) crudeness ['the crude weapons and rude agricultural implements of early man', 'primitive movies of the 1890s', 'primitive living conditions in the Appalachian mountains']\n", + "primitive crude.s.04 belonging to an early stage of technical development; characterized by simplicity and (often) crudeness ['the crude weapons and rude agricultural implements of early man', 'primitive movies of the 1890s', 'primitive living conditions in the Appalachian mountains']\n", + "primitive primitive.s.04 of or created by one without formal training; simple or naive in style ['primitive art such as that by Grandma Moses is often colorful and striking']\n", + "primitive generalized.s.01 not biologically differentiated or adapted to a specific function or environment ['the hedgehog is a primitive and generalized mammal']\n", + "primitive primitively.r.02 in a primitive style or manner ['rather primitively operated foundries']\n", + "primitive monera.n.01 prokaryotic bacteria and blue-green algae and various primitive pathogens; because of lack of consensus on how to divide the organisms into phyla informal names are used for the major divisions []\n", + "primitive trickster.n.03 a mischievous supernatural being found in the folklore of many primitive people; sometimes distinguished by prodigious biological drives and exaggerated bodily parts []\n", + "primitive hamamelidae.n.01 a group of chiefly woody plants considered among the most primitive of angiosperms; perianth poorly developed or lacking; flowers often unisexual and often in catkins and often wind pollinated; contains 23 families including the Betulaceae and Fagaceae (includes the Amentiferae); sometimes classified as a superorder []\n", + "pygmy massasauga.n.02 pygmy rattlesnake found in moist areas from the Great Lakes to Mexico; feeds on mice and small amphibians []\n", + "pygmy ground_rattler.n.01 small pygmy rattlesnake []\n", + "pygmy gowen_cypress.n.01 small sometimes shrubby tree native to California; often used as an ornamental; in some classification systems includes the pygmy cypress and the Santa Cruz cypress []\n", + "queer cosmopolitan.a.02 composed of people from or at home in many parts of the world; especially not provincial in attitudes or interests; - T.B. Macaulay ['his cosmopolitan benevolence impartially extended to all races and to all creeds', 'the ancient and cosmopolitan societies of Syria and Egypt', 'that queer, cosmopolitan, rather sinister crowd found around the Marseilles docks']\n", + "queer curious.s.01 beyond or deviating from the usual or expected ['a curious hybrid accent', 'her speech has a funny twang', 'they have some funny ideas about war', 'had an odd name', 'the peculiar aromatic odor of cloves', 'something definitely queer about this town', 'what a rum fellow', 'singular behavior']\n", + "queer fishy.s.02 not as expected ['there was something fishy about the accident', 'up to some funny business', 'some definitely queer goings-on', 'a shady deal', 'her motives were suspect', 'suspicious behavior']\n", + "queer rigout.n.01 a person's costume (especially if bizarre) ['What a queer rigout!']\n", + "race equal_opportunity.n.01 the right to equivalent opportunities for employment regardless of race or color or sex or national origin []\n", + "race supremacism.n.01 the belief that some particular group or race is superior to all others ['white supremacism']\n", + "race linguistic_profiling.n.01 using speech characteristics or dialect to identify a speaker's race or religion or social class []\n", + "race discussion.n.01 an extended communication (often interactive) dealing with some particular topic ['the book contains an excellent discussion of modal logic', 'his treatment of the race question is badly biased']\n", + "race racial_immunity.n.01 natural immunity shared by all members of a particular race []\n", + "races racial.a.02 of or characteristic of race or races or arising from differences among groups ['racial differences', 'racial discrimination']\n", + "races miscegenation.n.01 reproduction by parents of different races (especially by white and non-white persons) []\n", + "races ethnology.n.01 the branch of anthropology that deals with the division of humankind into races and with their origins and distribution and distinctive characteristics []\n", + "races race.n.03 people who are believed to belong to the same genetic stock ['some biologists doubt that there are important genetic differences between races of human beings']\n", + "retarded negative.s.03 having the quality of something harmful or unpleasant ['ran a negative campaign', 'delinquents retarded by their negative outlook on life']\n", + "retarded retarded.a.01 relatively slow in mental or emotional or physical development ['providing a secure and sometimes happy life for the retarded']\n", + "retarded backward.s.03 retarded in intellectual development []\n", + "retarded developmentally.r.01 with respect to development ['developmentally retarded']\n", + "retarded mentally_retarded.n.01 people collectively who are mentally retarded ['he started a school for the retarded']\n", + "retarded mentally_retarded.n.01 people collectively who are mentally retarded ['he started a school for the retarded']\n", + "retarded idiot_savant.n.01 person who is mentally retarded in general but who displays remarkable aptitude in some limited field (usually involving memory) []\n", + "retarded still's_disease.n.01 a form of rheumatoid arthritis that affects children; large joints become inflamed and bone growth may be retarded []\n", + "retarded pink.v.02 sound like a car engine that is firing too early ['the car pinged when I put in low-octane gasoline', 'The car pinked when the ignition was too far retarded']\n", + "second world research.v.02 inquire into ['the students had to research the history of the Second World War for their history project', 'He searched for information on his relatives on the web', 'Scientists are exploring the nature of consciousness']\n", + "servant domestic.a.02 of or relating to the home ['domestic servant', 'domestic science']\n", + "servant domestic.n.01 a servant who is paid to perform menial tasks around the household []\n", + "servant housekeeper.n.01 a servant who is employed to perform domestic task in a household []\n", + "servant skivvy.n.01 a female domestic servant who does all kinds of menial work []\n", + "servant serve.v.10 work for or be a servant to ['May I serve you?', 'She attends the old lady in the wheelchair', 'Can you wait on our table, please?', 'Is a salesperson assisting you?', 'The minister served the King for many years']\n", + "servants trustworthy.s.02 taking responsibility for one's conduct and obligations ['trustworthy public servants']\n", + "servants merit_system.n.01 the system of employing and promoting civil servants on the basis of ability []\n", + "servants spoils_system.n.01 the system of employing and promoting civil servants who are friends and supporters of the group in power []\n", + "servants retain.v.02 allow to remain in a place or position or maintain a property or feature ['We cannot continue several servants any longer', 'She retains a lawyer', \"The family's fortune waned and they could not keep their household staff\", 'Our grant has run out and we cannot keep you on', 'We kept the work going as long as we could', 'She retained her composure', 'this garment retains its shape even after many washings']\n", + "slave slave.n.03 someone entirely dominated by some influence or person ['a slave to fashion', 'a slave to cocaine', 'his mother was his abject slave']\n", + "slave slave.n.03 someone entirely dominated by some influence or person ['a slave to fashion', 'a slave to cocaine', 'his mother was his abject slave']\n", + "slave slave.n.03 someone entirely dominated by some influence or person ['a slave to fashion', 'a slave to cocaine', 'his mother was his abject slave']\n", + "slave clay.n.04 United States politician responsible for the Missouri Compromise between free and slave states (1777-1852) []\n", + "slave enslavement.n.01 the state of being a slave; --Shakespeare ['So every bondman in his own hand bears the power to cancel his captivity']\n", + "slaves servile.s.02 relating to or involving slaves or appropriate for slaves or servants [\"Brown's attempt at servile insurrection\", 'the servile wars of Sicily', 'servile work']\n", + "slaves antagonistic.s.02 characterized by antagonism or antipathy ['slaves antagonistic to their masters', 'antipathetic factions within the party']\n", + "slaves slavery.n.02 the practice of owning slaves []\n", + "slaves action.n.09 an act by a government body or supranational organization ['recent federal action undermined the segregationist position', 'the United Nations must have the power to propose and organize action without being hobbled by irrelevant issues', 'the Union action of emancipating Southern slaves']\n", + "slaves manumission.n.01 the formal act of freeing from slavery ['he believed in the manumission of the slaves']\n", + "slaves ku_klux_klan.n.01 a secret society of white Southerners in the United States; was formed in the 19th century to resist the emancipation of slaves; used terrorist tactics to suppress Black people []\n", + "slaves convert.v.02 change the nature, purpose, or function of something ['convert lead into gold', 'convert hotels into jails', 'convert slaves to laborers']\n", + "third world teeming.s.01 abundantly filled with especially living things [\"the Third World's teeming millions\", 'the teeming boulevard']\n", + "traditional traditional.a.01 consisting of or derived from tradition ['traditional history', 'traditional morality']\n", + "traditional traditional.a.01 consisting of or derived from tradition ['traditional history', 'traditional morality']\n", + "traditional traditional.s.02 pertaining to time-honored orthodox doctrines ['the simple security of traditional assumptions has vanished']\n", + "traditional mongoloid.a.02 of or pertaining to or characteristic of one of the traditional racial division of humankind including especially peoples of central and eastern Asia []\n", + "traditional kabbalism.n.02 adherence to some extreme traditional theological concept or interpretation []\n", + "traditional traditionalism.n.01 strict adherence to traditional methods or teachings []\n", + "traditional confucianism.n.01 the teachings of Confucius emphasizing love for humanity; high value given to learning and to devotion to family (including ancestors); peace; justice; influenced the traditional culture of China []\n", + "traditional neoconservatism.n.01 an approach to politics or theology that represents a return to a traditional point of view (in contrast to more liberal or radical schools of thought of the 1960s) []\n", + "traditional basque_homeland_and_freedom.n.01 a terrorist organization organized in 1959 by student activists who were dissatisfied with the moderate nationalism of the traditional Basque party; want to create an independent homeland in Spain's western Pyrenees ['in 1968 ETA launched a campaign of political assassinations of government officials']\n", + "traditional beat_generation.n.01 a United States youth subculture of the 1950s; rejected possessions or regular work or traditional dress; for communal living and psychedelic drugs and anarchism; favored modern forms of jazz (e.g., bebop) []\n", + "traditional tory.n.03 a supporter of traditional political and social institutions against the forces of reform; a political conservative []\n", + "trans elaidic_acid.n.01 a monounsaturated fatty acid that has the same structure as oleic acid except that it is a trans fatty acid; the major trans fatty acid in margarine and fried foods []\n", + "tribe zapotec.n.01 a member of a large tribe of Mesoamericans living in southern Mexico whose civilization flourished around 300 to 900 []\n", + "tribe menomini.n.01 a member of the federally recognized tribe of Algonquian people living on a reservation in central Wisconsin []\n", + "tribe inmarry.v.01 marry within one's own tribe or group ['The inhabitants of this isolated village tend to inmarry']\n", + "tribes shamanism.n.01 any animistic religion similar to Asian shamanism (especially as practiced by certain Native American tribes) []\n", + "tribes nation.n.04 a federation of tribes (especially Native American tribes) ['the Shawnee nation']\n", + "tribes amphictyony.n.01 an association of neighboring states or tribes in ancient Greece; established originally to defend a common religious center []\n", + "tribes chinook.n.02 a member of an important North American Indian people who controlled the mouth of the Columbia river; they were organized into settlements rather than tribes []\n", + "tribes indian_agent.n.01 a representative of the federal government to American Indian tribes (especially on Indian reservations) []\n", + "tribes tribalism.n.01 the state of living together in tribes []\n", + "western western.a.01 relating to or characteristic of the western parts of the world or the West as opposed to the eastern or oriental parts ['the western world', 'western thought']\n", + "western western.a.01 relating to or characteristic of the western parts of the world or the West as opposed to the eastern or oriental parts ['the western world', 'western thought']\n", + "western western.a.01 relating to or characteristic of the western parts of the world or the West as opposed to the eastern or oriental parts ['the western world', 'western thought']\n", + "western occidental.s.01 denoting or characteristic of countries of Europe and the western hemisphere ['occidental civilization', 'Hesperian culture']\n", + "western malay.a.01 of or relating to or characteristic of the people or language of Malaysia and the northern Malay Peninsula and parts of the western Malay Archipelago ['Malay peoples', 'Malayan syllable structure']\n", + "western west_african.n.01 a group of languages spoken in the extreme western part of West Africa []\n", + "western dichotomy.n.01 being twofold; a classification into two opposed parts or subclasses ['the dichotomy between eastern and western culture']\n", + "western world.n.02 people in general; especially a distinctive group of people with some shared interest ['the Western world']\n", + "western bengal.n.01 a region whose eastern part is now Bangladesh and whose western part is included in India []\n", + "western haiti.n.01 a republic in the West Indies on the western part of the island of Hispaniola; achieved independence from France in 1804; the poorest and most illiterate nation in the western hemisphere []\n", + "western darfur.n.01 an impoverished region of western Sudan ['Darfur was a semi-independent sultanate until 1917 and is ethnically distinct from central Sudan']\n", + "western athapaskan.n.01 a member of any of the North American Indian groups speaking an Athapaskan language and living in the subarctic regions of western Canada and central Alaska []\n", + "white white.a.02 of or belonging to a racial group having light skin coloration ['voting patterns within the white population']\n", + "white black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "white black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "white black-and-white.s.03 of a situation that is sharply divided into mutually exclusive categories ['he rejected a black-and-white world', 'there are no black-and-white certainties', 'there were no grey areas, you were either for him or against him, he was all black-and-white']\n", + "white prejudicial.a.02 tending to favor preconceived ideas ['the presence of discriminatory or prejudicial attitudes in the white population']\n", + "white miscegenation.n.01 reproduction by parents of different races (especially by white and non-white persons) []\n", + "white prerogative.n.01 a right reserved exclusively by a particular person or group (especially a hereditary or official right) ['suffrage was the prerogative of white adult males']\n", + "white supremacism.n.01 the belief that some particular group or race is superior to all others ['white supremacism']\n", + "white white_separatism.n.01 a social system in which white people live separately from members of other races []\n", + "whites white.s.05 restricted to whites only ['under segregation there were even white restrooms and white drinking fountains', 'a lily-white movement which would expel Negroes from the organization']\n", + "whites color_barrier.n.01 the barrier preventing Blacks from participating in various activities with whites []\n", + "whites color_bar.n.01 barrier preventing blacks from participating in various activities with whites []\n" + ] + } + ], + "source": [ + "# definitions and examples\n", + "case_4 = []\n", + "case_4_count = 0\n", + "for term, hits in pwn_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"definition\" or hit[\"found_in\"] == \"examples\":\n", + " case_4_count += 1\n", + " case_4.append(hit[\"synset_id\"])\n", + " print(term, hit[\"synset_id\"], hit[\"definition\"], hit[\"examples\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "370" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_4_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/pwn_case4.txt','w') as txt_file:\n", + " for l in case_4:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 5" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal native.n.01 ['native', 'indigen', 'indigene', 'aborigine', 'aboriginal']\n", + "aboriginal native.a.03 ['native', 'aboriginal']\n", + "aboriginal aboriginal.s.02 ['aboriginal', 'primal', 'primeval', 'primaeval', 'primordial']\n", + "barbarian savage.n.01 ['savage', 'barbarian']\n", + "barbarian peasant.n.03 ['peasant', 'barbarian', 'boor', 'churl', 'Goth', 'tyke', 'tike']\n", + "barbarian barbarian.s.01 ['barbarian', 'barbaric', 'savage', 'uncivilized', 'uncivilised', 'wild']\n", + "berber berber.n.01 ['Berber']\n", + "berber berber.n.02 ['Berber']\n", + "berbers berbers.n.01 ['Berbers', 'Arab-Berbers']\n", + "black black.a.02 ['black']\n", + "bombay mumbai.n.01 ['Mumbai', 'Bombay']\n", + "burma myanmar.n.01 ['Myanmar', 'Union_of_Burma', 'Burma']\n", + "calcutta kolkata.n.01 ['Kolkata', 'Calcutta']\n", + "caucasian caucasian.n.02 ['Caucasian', 'Caucasian_language']\n", + "caucasian caucasian.a.01 ['Caucasian', 'Caucasic']\n", + "caucasian caucasian.s.02 ['Caucasian', 'Caucasoid']\n", + "colored colored.a.01 ['colored', 'coloured', 'colorful']\n", + "colored colored.s.02 ['colored', 'coloured', 'negro']\n", + "colored bleached.s.02 ['bleached', 'colored', 'coloured', 'dyed']\n", + "descent origin.n.02 ['origin', 'descent', 'extraction']\n", + "descent descent.n.04 ['descent', 'line_of_descent', 'lineage', 'filiation']\n", + "descent lineage.n.01 ['lineage', 'line', 'line_of_descent', 'descent', 'bloodline', 'blood_line', 'blood', 'pedigree', 'ancestry', 'origin', 'parentage', 'stemma', 'stock']\n", + "disabled disabled.n.01 ['disabled', 'handicapped']\n", + "disabled disabled.s.01 ['disabled', 'handicapped']\n", + "discover detect.v.01 ['detect', 'observe', 'find', 'discover', 'notice']\n", + "discover learn.v.02 ['learn', 'hear', 'get_word', 'get_wind', 'pick_up', 'find_out', 'get_a_line', 'discover', 'see']\n", + "discover discover.v.03 ['discover', 'find']\n", + "discover discover.v.04 ['discover', 'find']\n", + "discover fall_upon.v.01 ['fall_upon', 'strike', 'come_upon', 'light_upon', 'chance_upon', 'come_across', 'chance_on', 'happen_upon', 'attain', 'discover']\n", + "discover unwrap.v.02 ['unwrap', 'disclose', 'let_on', 'bring_out', 'reveal', 'discover', 'expose', 'divulge', 'break', 'give_away', 'let_out', 'uncover']\n", + "discover discover.v.07 ['discover']\n", + "dwarf dwarf.n.01 ['dwarf', 'midget', 'nanus']\n", + "dwarf dwarf.n.03 ['dwarf']\n", + "eskimo eskimo.n.02 ['Eskimo', 'Esquimau']\n", + "ethnicity ethnicity.n.01 ['ethnicity']\n", + "exotic alien.s.02 ['alien', 'exotic']\n", + "exotic exotic.s.02 ['exotic']\n", + "footman footman.n.01 ['footman']\n", + "gay homosexual.n.01 ['homosexual', 'homophile', 'homo', 'gay']\n", + "gay gay.s.03 ['gay']\n", + "gay gay.s.06 ['gay', 'queer', 'homophile']\n", + "gypsy itinerant.n.01 ['itinerant', 'gypsy', 'gipsy']\n", + "gypsy gypsy.n.02 ['Gypsy', 'Gipsy', 'Romany', 'Rommany', 'Romani', 'Roma', 'Bohemian']\n", + "gypsy gypsy.n.03 ['gypsy', 'gipsy']\n", + "half-breed half-blooded.s.01 ['half-blooded', 'half-bred', 'half-breed']\n", + "handicap disability.n.01 ['disability', 'disablement', 'handicap', 'impairment']\n", + "handicap handicap.n.02 ['handicap']\n", + "handicap hindrance.n.01 ['hindrance', 'hinderance', 'deterrent', 'impediment', 'balk', 'baulk', 'check', 'handicap']\n", + "handicap disable.v.02 ['disable', 'invalid', 'incapacitate', 'handicap']\n", + "handicap handicap.v.02 ['handicap']\n", + "handicap handicap.v.03 ['handicap', 'hinder', 'hamper']\n", + "headhunter headhunter.n.02 ['headhunter', 'head-shrinker']\n", + "hermaphrodite hermaphrodite.n.01 ['hermaphrodite', 'intersex', 'gynandromorph', 'androgyne', 'epicene', 'epicene_person']\n", + "hermaphrodite hermaphroditic.s.02 ['hermaphroditic', 'hermaphrodite']\n", + "homo homosexual.n.01 ['homosexual', 'homophile', 'homo', 'gay']\n", + "homo homo.n.02 ['homo', 'man', 'human_being', 'human']\n", + "homosexual homosexual.n.01 ['homosexual', 'homophile', 'homo', 'gay']\n", + "homosexual homosexual.a.01 ['homosexual']\n", + "hottentot khoikhoin.n.01 ['Khoikhoin', 'Khoikhoi', 'Hottentot']\n", + "immigrant immigrant.n.01 ['immigrant']\n", + "indian indian.a.01 ['Indian']\n", + "indian indian.a.02 ['Indian', 'Amerind', 'Amerindic', 'Native_American']\n", + "indigenous autochthonal.s.01 ['autochthonal', 'autochthonic', 'autochthonous', 'endemic', 'indigenous']\n", + "kaffir great_millet.n.01 ['great_millet', 'kaffir', 'kafir_corn', 'kaffir_corn', 'Sorghum_bicolor']\n", + "lilliputian lilliputian.n.01 ['lilliputian']\n", + "lilliputian lilliputian.a.01 ['Lilliputian']\n", + "lilliputian bantam.s.01 ['bantam', 'diminutive', 'lilliputian', 'midget', 'petite', 'tiny', 'flyspeck']\n", + "maroon maroon.n.01 ['maroon']\n", + "maroon maroon.n.03 ['maroon']\n", + "maroon maroon.v.01 ['maroon', 'strand']\n", + "maroon maroon.v.02 ['maroon']\n", + "mestizo mestizo.n.01 ['mestizo']\n", + "metis metis.n.01 ['Metis']\n", + "mohammedan mohammedan.n.01 ['Mohammedan', 'Muhammedan', 'Muhammadan']\n", + "mohammedan muhammadan.a.01 ['Muhammadan', 'Mohammedan']\n", + "mongoloid mongoloid.n.01 ['Mongoloid']\n", + "mongoloid mongoloid.a.01 ['mongoloid']\n", + "mongoloid mongoloid.a.02 ['Mongoloid']\n", + "moor moor.n.01 ['Moor']\n", + "moor moor.n.02 ['moor', 'moorland']\n", + "mulatto mulatto.n.01 ['mulatto']\n", + "native native.a.01 ['native']\n", + "native native.a.03 ['native', 'aboriginal']\n", + "negro colored.s.02 ['colored', 'coloured', 'negro']\n", + "oriental oriental.s.01 ['oriental']\n", + "page page.n.05 ['page']\n", + "page page.n.06 ['page', 'varlet']\n", + "primitive primitive.n.01 ['primitive', 'primitive_person']\n", + "primitive primitive.n.02 ['primitive']\n", + "primitive crude.s.04 ['crude', 'primitive', 'rude']\n", + "primitive primitive.s.04 ['primitive', 'naive']\n", + "primitivism crudeness.n.01 ['crudeness', 'crudity', 'primitiveness', 'primitivism', 'rudeness']\n", + "primitivism primitivism.n.02 ['primitivism']\n", + "pygmy pygmy.n.01 ['pygmy', 'pigmy']\n", + "pygmy pygmy.n.02 ['Pygmy', 'Pigmy']\n", + "queer thwart.v.01 ['thwart', 'queer', 'spoil', 'scotch', 'foil', 'cross', 'frustrate', 'baffle', 'bilk']\n", + "queer queer.v.02 ['queer', 'expose', 'scupper', 'endanger', 'peril']\n", + "queer curious.s.01 ['curious', 'funny', 'odd', 'peculiar', 'queer', 'rum', 'rummy', 'singular']\n", + "queer gay.s.06 ['gay', 'queer', 'homophile']\n", + "race subspecies.n.01 ['subspecies', 'race']\n", + "retarded mentally_retarded.n.01 ['mentally_retarded', 'retarded', 'developmentally_challenged']\n", + "retarded retarded.a.01 ['retarded']\n", + "servant servant.n.01 ['servant', 'retainer']\n", + "slave slave.n.03 ['slave']\n", + "traditional traditional.a.01 ['traditional']\n", + "traditional traditional.s.02 ['traditional']\n", + "transvestite transvestite.n.01 ['transvestite', 'cross-dresser']\n", + "transvestite transvestic.a.01 ['transvestic', 'transvestite']\n", + "tribe tribe.n.01 ['tribe', 'folk']\n", + "western western.a.01 ['western']\n", + "white white.a.02 ['white']\n" + ] + } + ], + "source": [ + "# lemmas no markers\n", + "case_5 = []\n", + "case_5_count = 0\n", + "for term, hits in pwn_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"lemmata\":\n", + " # no markers\n", + " if hit[\"synset_id\"] not in pwn_implicit and hit[\"synset_id\"] not in pwn_explicit:\n", + " case_5_count += 1\n", + " case_5.append(hit[\"synset_id\"])\n", + " print(term, hit[\"synset_id\"], hit[\"lemmata\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "111" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_5_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/pwn_case5.txt','w') as txt_file:\n", + " for l in case_5:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "black black.n.05 ['Black', 'African-American', 'Negro', 'Negroid']\n", + "coolie coolie.n.01 ['coolie', 'cooly']\n", + "eskimo eskimo.n.01 ['Eskimo', 'Esquimau', 'Inuit']\n", + "half-breed half-breed.n.01 ['half-breed']\n", + "inuit eskimo.n.01 ['Eskimo', 'Esquimau', 'Inuit']\n", + "kaffir kaffir.n.02 ['kaffir', 'kafir', 'caffer', 'caffre']\n", + "lilliputian fiddling.s.01 ['fiddling', 'footling', 'lilliputian', 'little', 'niggling', 'piddling', 'piffling', 'petty', 'picayune', 'trivial']\n", + "madras tamil_nadu.n.01 ['Tamil_Nadu', 'Madras']\n", + "madras chennai.n.01 ['Chennai', 'Madras']\n", + "mongoloid mongoloid.n.02 ['mongoloid']\n", + "mongoloid mongoloid.a.03 ['mongoloid']\n", + "negro black.n.05 ['Black', 'African-American', 'Negro', 'Negroid']\n", + "queer fagot.n.01 ['fagot', 'faggot', 'fag', 'fairy', 'nance', 'pansy', 'queen', 'queer', 'poof', 'poove', 'pouf']\n" + ] + } + ], + "source": [ + "# lemmas with markers\n", + "case_5_markers = []\n", + "case_5_markers_count = 0\n", + "for term, hits in pwn_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"lemmata\":\n", + " # no markers\n", + " if hit[\"synset_id\"] in pwn_implicit or hit[\"synset_id\"] in pwn_explicit:\n", + " case_5_markers_count += 1\n", + " case_5_markers.append(hit[\"synset_id\"])\n", + " print(term, hit[\"synset_id\"], hit[\"lemmata\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "13" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_5_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/pwn_case5_with_markers.txt','w') as txt_file:\n", + " for l in case_5_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## ODWN" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [], + "source": [ + "# import subset\n", + "with open(\"/Users/anesterov/reps/LODlit/ODWN/odwn_subset.json\",'r') as jf:\n", + " odwn_subset = json.load(jf)" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [], + "source": [ + "odwn_implicit = implicit_markers[implicit_markers[\"resource\"] == \"odwn\"][\"entity_id\"].to_list()\n", + "odwn_explicit = explicit_markers[explicit_markers[\"resource\"] == \"odwn\"][\"entity_id\"].to_list()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 4" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "afkomst eng-30-04923743-n geografische of etnische oorsprong ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['ze is van Russische afkomst', 'dit woord is van Grieks-Latijnse afkomst', 'ik ben wie ik ben en ik kan mijn afkomst niet verloochenen', 'van een (bepaalde) afkomst [zijn]']\n", + "afkomst eng-30-04923743-n geografische of etnische oorsprong ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['ze is van Russische afkomst', 'dit woord is van Grieks-Latijnse afkomst', 'ik ben wie ik ben en ik kan mijn afkomst niet verloochenen', 'van een (bepaalde) afkomst [zijn]']\n", + "afkomst eng-30-04923743-n geografische of etnische oorsprong ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['ze is van Russische afkomst', 'dit woord is van Grieks-Latijnse afkomst', 'ik ben wie ik ben en ik kan mijn afkomst niet verloochenen', 'van een (bepaalde) afkomst [zijn]']\n", + "afkomst eng-30-04923743-n geografische of etnische oorsprong ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['ze is van Russische afkomst', 'dit woord is van Grieks-Latijnse afkomst', 'ik ben wie ik ben en ik kan mijn afkomst niet verloochenen', 'van een (bepaalde) afkomst [zijn]']\n", + "afkomst eng-30-04923743-n afkomst ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['een paard van onbekende afstamming']\n", + "afkomst odwn-10-104552692-v zich laten voorstaan op ['zich laten voorstaan op'] ['je erop beroemen dat je stevig hebt bijgedragen tot de emancipatie van de vrouw', 'je erop beroemen dat je van adellijke afkomst bent', 'zich beroemen op zijn talent voor organisatie']\n", + "afkomst eng-30-04923743-n afkomst ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['iemand van geboorte', 'van hoge/lage geboorte']\n", + "afkomst odwn-10-107675980-v schamen ['schamen'] ['hij geneerde zich voor zijn afkomst/broer', 'zich generen voor iets/iemand', 'geneer je niet!']\n", + "afkomst eng-30-07970721-n mensen met gemeenschappelijke afkomst ['verzameling van bloedverwanten', 'mensen met gemeenschappelijke afkomst', 'geslacht van mensen', 'familietak', 'alle mensen van één geslacht', 'deel v.e. familie'] ['het geslacht van de Bourbons', 'stammen uit een nobel/adellijk geslacht', 'van een voornaam geslacht', 'tot een rijk/adellijk/aanzienlijk/oud geslacht behoren']\n", + "afkomst eng-30-10157549-n persoon van gemengde afkomst ['persoon van gemengde afkomst', 'kind van verschillende rassen'] []\n", + "afkomst odwn-10-106166180-v pralen ['pralen'] ['met zijn adellijke afkomst koketteren', 'met zijn slordigheid koketteren']\n", + "afkomst eng-30-04923743-n afkomst ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] ['van goede komaf zijn', 'van goede/gewone/simpele komaf zijn']\n", + "afkomst eng-30-01774799-v verachten ['verachten', 'iemand minderwaardig vinden', 'minderwaardig vinden'] ['iemand minachten vanwege zijn of haar afkomst']\n", + "afkomst eng-30-10577284-n iemand die (beroepsmatig) verkoopt ['iemand die (beroepsmatig) verkoopt'] ['op genoemd tijdstip bevonden zich volgens de verkoper twee mannen in de winkel, die naar eigen zeggen van Franse afkomst waren', 'de koop is pas geldig als de koper en de verkoper beiden getekend hebben']\n", + "afkomst eng-30-07970721-n None ['verzameling van bloedverwanten', 'mensen met gemeenschappelijke afkomst', 'geslacht van mensen', 'familietak', 'alle mensen van één geslacht', 'deel v.e. familie'] None\n", + "afkomst eng-30-10157549-n None ['persoon van gemengde afkomst', 'kind van verschillende rassen'] None\n", + "afkomst eng-30-04923743-n None ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] None\n", + "afkomst eng-30-04923743-n None ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] None\n", + "afkomst eng-30-04923743-n None ['geografische of etnische oorsprong', 'afkomst', 'afkomst', 'afkomst', 'begin, startpunt'] None\n", + "allochtonen odwn-10-101546688-n immigrant ['immigrant'] ['de integratie van allochtonen in de Nederlandse samenleving']\n", + "allochtonen eng-30-13980288-n vijandigheid ['vijandigheid', 'vijandige houding', 'het vijand zijn met iemand'] ['in de klas heerste een sfeer van onderlinge animositeit', 'een sfeer van onderlinge animositeit', '(de) animositeit jegens [allochtonen]', 'de animositeit tussen [de echtelieden]']\n", + "allochtonen eng-30-13427078-n aanpassing ['aanpassing', 'proces of resultaat van aanpassing', 'aanpassing', 'iets dat wijzigt of gewijzigd is'] ['gedwongen assimilatie', 'de assimilatie van allochtonen aan de Nederlandse cultuur verloopt soms moeizaam', 'assimilatie aan [de Nederlandse cultuur]']\n", + "allochtonen eng-30-07959269-n opeenhoping ['opeenhoping', '(verkeers)opstopping', 'tot een hoop gevormde verzameling'] ['de grootste concentratie allochtonen is te vinden in probleemwijkende grootste concentratie allochtonen is te vinden in probleemwijken']\n", + "allochtonen eng-30-01237415-n het samengaan en één worden ['het samengaan en één worden'] ['de integratie van allochtonen in onze cultuur verloopt niet zonder slag of stoot', 'integratie in (onze cultuur)', 'de integratie bevorderen', 'de Europese integratie']\n", + "barbaren eng-30-10553402-n woesteling ['woesteling', 'bloeddorstig persoon', 'natuurliefhebber', 'primitief iemand'] ['de barbaren op de voetbaltribunes', 'een barbaar die zijn hond schopt']\n", + "barbaren eng-30-00386390-v bekeren ['bekeren'] ['barbaren kerstenen']\n", + "bediend eng-30-05892651-n voorwaarde om in aanmerking te komen voor iets ['voorwaarde om in aanmerking te komen voor iets'] ['topsport stelt hoge eisen aan het menselijk lichaam', 'eisen stellen aan', 'volgens de eisen van betamelijkheid dienen de dames aan tafel eerst te worden bediend', 'volgens de eisen van betamelijkheid', 'een goede fiets moet aan een aantal eisen voldoen', 'aan eisen voldoen']\n", + "bediend odwn-10-109911010-n winkelbediende ['winkelbediende'] ['een gerant aanspreken om bediend te worden']\n", + "bediende eng-30-02396205-v in een functie benoemen ['in een functie benoemen', 'functie of status verlenen', 'een ambt toekennen', 'in een positie brengen'] ['er werd een nieuwe bediende aangesteld', 'een bediende aanstellen', 'de gewezen wereldreiziger werd als burgemeester aangesteld', 'iemand als [burgemeester] aanstellen']\n", + "bediende eng-30-02396205-v in een functie benoemen ['in een functie benoemen', 'functie of status verlenen', 'een ambt toekennen', 'in een positie brengen'] ['er werd een nieuwe bediende aangesteld', 'een bediende aanstellen', 'de gewezen wereldreiziger werd als burgemeester aangesteld', 'iemand als [burgemeester] aanstellen']\n", + "bediende odwn-10-103725642-v wegdoen ['wegdoen'] ['ik heb mijn job als bediende afgestoten', 'een baan afstoten', 'het Ziekenfonds ziet zich genoodzaakt enkele zorgtaken af te stoten', 'taken afstoten', 'bij defensie gaat men de Leopardtank afstoten', 'materieel afstoten', 'bij de fusie worden de met verlies draaiende divisies afgestoten', 'een divisie afstoten']\n", + "bediende eng-30-10053808-n winkel-, kantoorbediende ['werknemer', 'werknemer', 'winkel-, kantoorbediende', 'werknemer', 'iemand die werkt tegen betaling', 'vermogen te werken', 'iemand die ergens in loondienst is'] ['de jongste bediende']\n", + "bediende eng-30-10582154-n huisbediende ['huisbediende'] ['een bediende in livrei']\n", + "bediende eng-30-00874537-v vertrouwd maken ['vertrouwd maken'] ['de nieuwe bediende inwerken', 'iemand inwerken in een functie']\n", + "bediende eng-30-09928451-n bediende op kantoor ['kantoorbediende', 'bediende op kantoor'] []\n", + "bediende odwn-10-101393848-n uniform voor huispersoneel ['uniform voor huispersoneel'] ['(een bediende) in livrei']\n", + "bediende odwn-10-105858995-v werk geven ['werk geven'] ['iemand tewerkstellen als [eerste bediende bij de bank]']\n", + "bediende eng-30-09928451-n None ['kantoorbediende', 'bediende op kantoor'] None\n", + "birma eng-30-07972425-n feodaal bestuursstelsel ['feodaal bestuursstelsel', 'Middeleeuws staatsbestel'] ['het middeleeuwse feodalisme', 'het feodalisme in Birma moet bestreden worden']\n", + "blank eng-30-04752221-n eigenschap van niet gelijk zijn ['eigenschap van niet gelijk zijn'] ['sociale/maatschappelijke ongelijkheid', 'ongelijkheid tussen [zwart] en [blank]', 'ongelijkheid in [de verdeling]']\n", + "blank odwn-10-103281025-v in een bepaalde toestand zijn ['in een bepaalde toestand zijn'] ['bekend staan als [zangeres]', 'op springen staan', 'aan het hoofd van iets staan', 'aan het roer van iets staan', 'in bloei staan', 'in brand staan', 'in dubio staan', \"op straat/'de keien' staan\", 'voor gek/paal staan', 'op stapel staan', 'in verbinding staan met iets/iemand', 'in je recht staan', 'hoog aangeschreven staan', 'bol staan van [de fouten]', 'blank staan', 'op de bank staan', 'dat komt je nog duur te staan!', 'er staat je/hem/haar iets te wachten', 'iemand te woord staan', 'op je strepen/ponteneur staan', 'onder curatele staan']\n", + "blanke eng-30-05238282-n weefsellaag die het lichaam bedekt ['weefsellaag die het lichaam bedekt', 'huid van mensen of dieren'] ['huiden van wilde dieren', 'een gerimpelde huid', 'een gave huid', 'een getaande huid', 'een gebronsde/gebruinde huid', 'deze crème is vooral voor de vette of gecombineerde huid', 'een [vette/gecombineerde/droge] huid', 'dit scheerschuim is speciaal voor de gevoelige huid', 'de gevoelige huid', 'een donkere/blanke huid']\n", + "blanke odwn-10-100513750-n kruising v.e. blanke en een indiaan ['kruising v.e. blanke en een indiaan'] []\n", + "blanke odwn-10-103063347-n toestand van onderdrukking ['toestand van onderdrukking'] ['[blanke/Chinese] overheersing']\n", + "blanke eng-30-09976551-n uitgebuite vrouw ['v.e. ander afhankelijk persoon', 'uitgebuite vrouw'] ['blanke slavinnen']\n", + "blanke r_n-41437 bevolkingsgroep [] ['het zwarte/Joodse/blanke volksdeel']\n", + "blanke odwn-10-100513750-n None ['kruising v.e. blanke en een indiaan'] None\n", + "blanken eng-30-10157549-n kind van verschillende rassen ['persoon van gemengde afkomst', 'kind van verschillende rassen'] ['zwarten, blanken en kleurlingen']\n", + "blanken odwn-10-100481401-n gelijkheid voor de wet ['gelijkheid voor de wet'] ['rechtszekerheid en rechtsgelijkheid', 'rechtsgelijkheid van blanken en kleurlingen']\n", + "derde wereld eng-30-01207609-n het helpen ['hulp', 'hulp', 'het helpen', 'zorg voor mensen in nood', 'het samenwerken aan iets'] ['bedankt voor je hulp', 'voor veel mensen kwam de hulp echter te laat', 'humanitaire hulp', 'hulp voor [oorlogsslachtoffers]', 'om hulp roepen/vragen', 'hulp aan [de derde wereld]', 'ze hebben de hulp van een psychiater ingeroepen', 'hulp inroepen van iemand', '[dringend] hulp nodig hebben', 'zonder hulp van buiten redden we het niet', 'hulp van buiten', 'eerste hulp bij ongelukken (EHBO)', 'professionele hulp', 'hulp verlenen', 'iemand te hulp schieten/komen', 'hulp zoeken']\n", + "derde wereld odwn-10-104668187-n werk door kinderen ['werk door kinderen'] ['in de Derde wereld wordt nog veel kinderarbeid verricht', 'kinderarbeid verrichten']\n", + "derde wereld eng-30-09178999-n dat wat je ergens toe aanzet ['voor- en nadelen tegen elkaar opwegen', 'motief', 'overweging', 'beweegreden', 'beweegreden, motief voor iemands daden', 'dat wat je ergens toe aanzet', 'dat wat je ergens toe aanzet', 'reden', 'zedelijke grond'] ['Wat was je motivatie om vrijwilligerswerk in een Derde Wereld land te willen doen?']\n", + "derde wereld odwn-10-107188952-n project van ontwikkeling in Derde Wereld ['project van ontwikkeling in Derde Wereld'] []\n", + "derde wereld odwn-10-106126041-v bevorderen ['bevorderen'] ['ze organiseerden die markt vooral om producten uit de Derde Wereld te promoten', 'producten promoten', \"met deze 'dag van het orgel' willen de organisatoren het orgel promoten\", 'het orgel promoten']\n", + "derde wereld odwn-10-107188952-n None ['project van ontwikkeling in Derde Wereld'] None\n", + "dwergen eng-30-09541125-n klein wezen uit een sprookje ['dwergachtige aardgeest', 'klein wezen uit een sprookje', 'klein mannetje uit sprookjes'] ['Sneeuwwitje en de zeven dwergen']\n", + "dwergen eng-30-03929202-n scherp en puntig werktuig ['scherp en puntig werktuig', 'houweel met punt en beitel'] ['met hun houwelen over de schouder marcheerden de zeven dwergen naar huis']\n", + "eskimo's r_n-40975 recht om te vissen [] ['de overheid heeft hen het visrecht verleend', 'het visrecht aan iemand verlenen', \"de Canadese Eskimo's krijgen hier de volgende zes jaren het visrecht\", 'het visrecht hebben/krijgen']\n", + "etnische groepen odwn-10-107289312-n hernieuwde vrede ['hernieuwde vrede'] ['een verzoening tot stand brengen', 'een verzoening tussen de verschillende etnische groepen', 'Na lang overleg hebben de regeringsleiders tot verzoening kunnen komen', 'tot verzoening komen']\n", + "gehandicapte eng-30-05689249-n belemmering, barrière ['belemmering', 'hindernis', 'bezwaar', 'onwenselijke omstandigheid', 'belemmering, hindernis', 'belemmering, barrière', 'iets dat in de weg staat', 'iets dat je hindert je doel te bereiken', 'probleem', 'hindernis', 'iets dat belemmert', 'belemmering', 'het verhinderen/verhinderd zijn'] ['geldgebrek is de grootste handicap voor gehandicapte sporters']\n", + "gehandicapte odwn-10-104805949-n lichamelijk gehandicapte ['lichamelijk gehandicapte'] ['voorzieningen voor invaliden']\n", + "gehandicapte eng-30-10352299-n elk ander mens ['buurman- of vrouw', 'man naast je', 'vrouw naast je', 'elk ander mens', 'evenmens', 'dame naast wie je zit bij een diner', 'heer naast wie je zit bij een diner'] ['de gehandicapte/zieke medemens']\n", + "gehandicapte odwn-10-104805949-n None ['lichamelijk gehandicapte'] None\n", + "gehandicapten eng-30-10158756-n iemand met een handicap ['iemand met een handicap'] ['een instelling voor geestelijk gehandicapten', 'de integratie van gehandicapten', 'voorzieningen voor gehandicapten', 'lichamelijk/geestelijk gehandicapte', '[zwaar/licht] gehandicapten']\n", + "gehandicapten eng-30-10158756-n iemand met een handicap ['iemand met een handicap'] ['een instelling voor geestelijk gehandicapten', 'de integratie van gehandicapten', 'voorzieningen voor gehandicapten', 'lichamelijk/geestelijk gehandicapte', '[zwaar/licht] gehandicapten']\n", + "gehandicapten eng-30-10158756-n iemand met een handicap ['iemand met een handicap'] ['een instelling voor geestelijk gehandicapten', 'de integratie van gehandicapten', 'voorzieningen voor gehandicapten', 'lichamelijk/geestelijk gehandicapte', '[zwaar/licht] gehandicapten']\n", + "gehandicapten eng-30-10158756-n iemand met een handicap ['iemand met een handicap'] ['een instelling voor geestelijk gehandicapten', 'de integratie van gehandicapten', 'voorzieningen voor gehandicapten', 'lichamelijk/geestelijk gehandicapte', '[zwaar/licht] gehandicapten']\n", + "gehandicapten r_n-17866 folder met informatie [] ['een informatiefolder over nieuwe koophuizen', 'een informatiefolder voor gehandicapten over aangepast vervoer', 'een informatiefolder verspreiden']\n", + "gehandicapten r_n-18195 toilet voor gehandicapten [] ['een invalidentoilet is meestal voorzien van extra beugels waaraan je je kunt vasthouden']\n", + "gehandicapten eng-30-02437707-v zorgen voor ['ontfermen', 'zorgen voor'] ['de zusters ontfermden zich over weeskinderen en gehandicapten in deze stad', 'zich ontfermen over weeskinderen en gehandicapten']\n", + "gehandicapten eng-30-02437707-v zorgen voor ['ontfermen', 'zorgen voor'] ['de zusters ontfermden zich over weeskinderen en gehandicapten in deze stad', 'zich ontfermen over weeskinderen en gehandicapten']\n", + "gehandicapten odwn-10-102949140-n vereniging ['vereniging'] ['een organisatie voor [dierenbescherming/gehandicapten]', 'binnen de organisatie is er een open persoonlijke sfeer', 'in/binnen een organisatie']\n", + "gehandicapten odwn-10-103405559-n inrichting al dan niet met verzorging ['inrichting al dan niet met verzorging'] ['een tehuis voor [schipperskinderen/verstandelijk gehandicapten]', 'in een tehuis', 'een gezinsvervangend tehuis']\n", + "gehandicapten eng-30-05139094-n moreel slechte hoedanigheid ['onvolkomenheid', 'slechte eigenschap', 'ondeugend iemand', 'moreel slechte hoedanigheid', 'gebrek', 'gebied waarop iemand gevoelig is', 'gebied waarop iemand te makkelijk is'] ['Oogzorg gehandicapten schiet tekort.']\n", + "gekleurd odwn-10-104127784-n afvalbak ['afvalbak'] ['een container voor gekleurd glas', 'textiel in de container gooien', 'een container (laten) plaatsen']\n", + "gekleurd eng-30-14881303-n harde doorzichtige stof ['harde doorzichtige stof'] ['gekleurd glas', 'komkommer worden achter glas gekweekt', 'achter glas', 'gerookt glas', 'getint glas', 'glas in lood', 'de meeste huizen hebben inmiddels dubbel glas', 'dubbel glas', 'glas gieten', 'mat glas', 'geblazen glas']\n", + "gekleurd odwn-10-101073990-n afvalbak voor glas ['afvalbak voor glas'] ['het glas naar de glasbak brengen', 'een glasbak voor gekleurd/wit glas']\n", + "gekleurd eng-30-03648219-n was ['te wassen goed', 'was'] ['gekleurd/wit wasgoed']\n", + "gekleurd r_n-42491 fontein op muziek, met gekleurd licht [] []\n", + "gekleurde odwn-10-100117009-n opening in een seinarm waarin een gekleurde ruit geplaatst kan worden ['opening in een seinarm waarin een gekleurde ruit geplaatst kan worden'] ['Er zit een oranje plaat in de bril van seinarm.']\n", + "gekleurde odwn-10-106678037-n gekleurde vlies met pupil in het oog ['gekleurde vlies met pupil in het oog'] []\n", + "gekleurde eng-30-04589745-n klein stuk glas dat in een venster is geplaatst ['plaat glas', 'klein stuk glas dat in een venster is geplaatst'] ['Er zitten drie gekleurde ruitjes in hun voordeur.']\n", + "gekleurde c_545556 smalle strook [] ['Het vliegtuig liet witte strepen achter in de lucht.', 'Donker haar met blonde strepen.', 'Een trui met gekleurde strepen.', 'Een streep licht viel door een kier naar binnen.']\n", + "gekleurde odwn-10-106133313-n gekleurde doek als symbool ['gekleurde doek als symbool'] []\n", + "gekleurde odwn-10-100117009-n None ['opening in een seinarm waarin een gekleurde ruit geplaatst kan worden'] None\n", + "gekleurde odwn-10-106133313-n None ['gekleurde doek als symbool'] None\n", + "gekleurde odwn-10-106678037-n None ['gekleurde vlies met pupil in het oog'] None\n", + "handicap odwn-10-108706678-v als onvermijdelijk aanvaarden ['iets accepteren, ergens mee akkoord gaan', 'als onvermijdelijk aanvaarden', 'aanvaarden', 'niet opkomen tegen', 'goedvinden'] ['een fysieke handicap is moeilijk te accepteren', 'je moet accepteren dat je ouder wordt', 'accepteren dat ...', 'ik kan jouw grove taal niet accepteren', 'grove taal (niet) accepteren']\n", + "handicap eng-30-10158756-n iemand met een handicap ['iemand met een handicap'] ['een instelling voor geestelijk gehandicapten', 'de integratie van gehandicapten', 'voorzieningen voor gehandicapten', 'lichamelijk/geestelijk gehandicapte', '[zwaar/licht] gehandicapten']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-14052403-n fysieke of mentale invaliditeit ['ziekte aan een bepaald lichaamsdeel', 'onvolkomenheid', 'fysieke of mentale invaliditeit', 'iets dat last geeft'] ['een lichamelijke/verstandelijke handicap', 'door zijn handicap moet hij in een rolstoel zitten', 'wij organiseren actieve zeilvakanties voor mensen met een handicap', 'met een handicap', 'een zware handicap', 'een lichte handicap']\n", + "handicap eng-30-05689249-n belemmering, barrière ['belemmering', 'hindernis', 'bezwaar', 'onwenselijke omstandigheid', 'belemmering, hindernis', 'belemmering, barrière', 'iets dat in de weg staat', 'iets dat je hindert je doel te bereiken', 'probleem', 'hindernis', 'iets dat belemmert', 'belemmering', 'het verhinderen/verhinderd zijn'] ['geldgebrek is de grootste handicap voor gehandicapte sporters']\n", + "handicap odwn-10-107547362-n het hebben v.e. lichamelijke handicap ['het hebben v.e. lichamelijke handicap'] ['veel mensen zijn arbeidsongeschikt als gevolg van ziekte of invaliditeit', 'blijvende invaliditeit']\n", + "handicap eng-30-10158756-n None ['iemand met een handicap'] None\n", + "handicap odwn-10-107547362-n None ['het hebben v.e. lichamelijke handicap'] None\n", + "handicaps eng-30-00849080-v belachelijk maken ['belachelijk maken'] ['in de voorstelling spotten de acteurs met onze dagelijkse vooroordelen', 'spotten met [vooroordelen/uiterlijkheden/handicaps]', 'daar moet je niet mee spotten', 'spot er maar mee!', 'daarmee valt niet te spotten']\n", + "homo eng-30-10076033-n homo ['homo', 'homoseksuele man', 'homoseksueel', 'homofiel'] ['vuile flikker!']\n", + "homo r_n-16996 mens [] ['homo sapiens']\n", + "homo eng-30-10076033-n None ['homo', 'homoseksuele man', 'homoseksueel', 'homofiel'] None\n", + "homo's odwn-10-109472945-n toekenning van gelijke rechten ['toekenning van gelijke rechten'] ['de emancipatie van de slaven in de 19e eeuw', \"de emancipatie van de vrouw/ouderen/homo's\"]\n", + "homo's eng-30-10173895-n heteroseksueel persoon ['heteroseksueel persoon', 'heteroseksueel persoon', 'heterofiel persoon'] [\"de Roze Panter is ook voor hetero's wel een leuke discotheek\", \"zowel hetero's als homo's worden geconfronteerd met de noodzaak tot safe sex\"]\n", + "homo's eng-30-10182913-n homoseksueel persoon ['homoseksueel persoon', 'homoseksueel persoon', 'homofiel persoon'] [\"de wet staat nog geen huwelijken toe tussen homo's\", \"de president wil een einde maken aan het weren van homo's uit het leger\", \"homo's en lesbo's\"]\n", + "homo's eng-30-10182913-n homoseksueel persoon ['homoseksueel persoon', 'homoseksueel persoon', 'homofiel persoon'] [\"de wet staat nog geen huwelijken toe tussen homo's\", \"de president wil een einde maken aan het weren van homo's uit het leger\", \"homo's en lesbo's\"]\n", + "homo's eng-30-10182913-n homoseksueel persoon ['homoseksueel persoon', 'homoseksueel persoon', 'homofiel persoon'] [\"de wet staat nog geen huwelijken toe tussen homo's\", \"de president wil een einde maken aan het weren van homo's uit het leger\", \"homo's en lesbo's\"]\n", + "homo's odwn-10-105972128-n beweging van homo's [\"beweging van homo's\"] []\n", + "homo's eng-30-10254965-n lesbische vrouw ['lesbische vrouw', 'lesbische vrouw', 'lesbische vrouw'] [\"homo's en lesbiennes\"]\n", + "homo's eng-30-10254965-n lesbische vrouw ['lesbische vrouw', 'lesbische vrouw', 'lesbische vrouw'] [\"homo's en lesbo's\"]\n", + "homo's odwn-10-105972128-n None [\"beweging van homo's\"] None\n", + "homoseksueel eng-30-00844254-n seksuele betrekkingen tussen mensen ['coïtus', 'geslachtsgemeenschap', 'paring', 'geslachtsgemeenschap', 'omgang met iemand', 'het paren', 'seksuele betrekkingen tussen mensen', 'geslachtsgemeenschap', 'seksuele omgang', 'seks'] ['heteroseksueel/homoseksueel geslachtsverkeer', 'geslachtsverkeer met jonge kinderen is strafbaar in Nederland', 'geslachtsverkeer met jonge kinderen']\n", + "homoseksuele eng-30-04623113-n persoonlijke aard ['geheel van onderliggende eigenschappen', 'persoonlijke aard', 'algemene gemoedstoestand', 'karakter', 'persoonlijkheid', 'eigenschappen van levende wezens', 'aard'] ['iemands persoonlijke/fundamentele geaardheid', 'uitkomen voor zijn geaardheid', 'seksuele geaardheid', 'homoseksuele geaardheid']\n", + "homoseksuele eng-30-10076033-n homoseksuele man ['homo', 'homoseksuele man', 'homoseksueel', 'homofiel'] []\n", + "homoseksuele eng-30-10076033-n None ['homo', 'homoseksuele man', 'homoseksueel', 'homofiel'] None\n", + "homoseksuelen odwn-10-109248619-n vereniging voor homoseksuelen ['vereniging voor homoseksuelen'] []\n", + "homoseksuelen r_n-24975 bar waar homoseksuelen komen [] []\n", + "homoseksuelen odwn-10-109248619-n None ['vereniging voor homoseksuelen'] None\n", + "inboorlingen odwn-10-106171034-n oorspronkelijke bewoner v.e. land ['oorspronkelijke bewoner v.e. land'] ['dr. Livingstone bezocht de inboorlingen in de jungle van Afrika']\n", + "indiaan odwn-10-100513750-n kruising v.e. blanke en een indiaan ['kruising v.e. blanke en een indiaan'] []\n", + "indiaan odwn-10-100513750-n None ['kruising v.e. blanke en een indiaan'] None\n", + "indianen odwn-10-107563512-v tot een overtuiging brengen ['tot een overtuiging brengen'] ['de indianen bekeren']\n", + "indianen odwn-10-102987666-v wonen in of op ['wonen in of op'] ['een huis/boerderij/hoeve bewonen', 'dat gebied werd vroeger bewoond door indianen', 'een gebied bewonen']\n", + "indianen r_v-3090 koopmanszaken doen [] ['handeldrijven met [het Westen/Kenia/de indianen]']\n", + "indianen odwn-10-101961229-n verhaal over indianen ['verhaal over indianen'] ['als kleine jongen las hij graag indianenverhalen', 'indianenverhalen lezen']\n", + "indianen eng-30-02635659-v teken of indruk achterlaten ['als blijk van iets achter doen blijven', 'teken of indruk achterlaten'] ['een goede indruk nalaten', 'haar tweejarige verblijf bij de Indianen heeft diepe sporen nagelaten', '(diepe) sporen nalaten', 'het landijs heeft diepe sporen in het landschap nagelaten', 'diepe sporen nalaten']\n", + "indianen odwn-10-104880448-v van de schedelhuid ontdoen ['van de schedelhuid ontdoen'] ['volgens de overleveringen zouden de indianen doorgaans hun vijanden scalperen', 'vijanden scalperen']\n", + "indianen eng-30-04458633-n aan goden gewijde paal ['aan goden gewijde paal'] ['de indianen bonden het slachtoffer aan de totempaal vast']\n", + "indianen eng-30-02503803-v uit een gebied voorgoed wegsturen ['in de ban doen', 'uit een gebied voorgoed wegsturen'] ['dissidenten naar Siberië verbannen', 'indianen uit hun woongebieden verbannen']\n", + "indianen odwn-10-101961229-n None ['verhaal over indianen'] None\n", + "indisch eng-30-08673039-n Indisch dorp ['Indisch dorp'] ['in de kampong']\n", + "indisch eng-30-10505732-n bepaald Indisch vorst ['bepaald Indisch vorst'] []\n", + "indisch r_n-38724 West-Indisch gerecht [] []\n", + "indisch r_n-39603 mogelijke oplossing bij schaken, dammen [] ['beiden speelden voorzichtig in een variant van de Franse verdediging', \"Timman speelde een variant van ['het Spaans'/'de Siciliaan'/'het Konings-Indisch']\"]\n", + "indisch eng-30-10505732-n None ['bepaald Indisch vorst'] None\n", + "indisch eng-30-08673039-n None ['Indisch dorp'] None\n", + "indische odwn-10-101655623-n Indische vogel ['Indische vogel'] []\n", + "indische eng-30-08058098-n handelsvennootschap ['handelsvennootschap', 'commercieel bedrijf'] ['in compagnie handelen', 'Verenigde Oost-Indische Compagnie']\n", + "indische eng-30-07557434-n voedsel bereid voor één gang ['voedsel bereid voor één gang', 'gerecht'] ['Chinese/Indische/Franse gerechten', 'een gerecht klaarmaken/opdienen', 'exotische gerechten']\n", + "indische eng-30-14917635-n vloeistof o.a. om mee te schrijven ['vloeistof o.a. om mee te schrijven'] ['met inkt schrijven', 'Oost-Indische inkt', 'zij had haar postcode met onzichtbare inkt op haar bezittingen geschreven', 'onzichtbare inkt', 'Chinese inkt', 'een pot inkt']\n", + "indische eng-30-02503517-n groot grijs zoogdier met slagtanden ['olifant', 'groot grijs zoogdier met slagtanden'] ['de Indische/Aziatische olifant', 'de Afrikaanse olifant']\n", + "indische eng-30-07557434-n gerecht ['voedsel bereid voor één gang', 'gerecht'] ['we serveren zowel Indische als Chinese schotels', 'een schotel serveren']\n", + "indische eng-30-12401684-n tropische boomsoort ['vijgenboom', 'tropische boomsoort'] ['de Indische/wilde vijgenboom']\n", + "indische odwn-10-101655623-n None ['Indische vogel'] None\n", + "indo odwn-10-104600207-n Indo-Germaanse taalfamilie ['Indo-Germaanse taalfamilie'] []\n", + "indo odwn-10-104600207-n None ['Indo-Germaanse taalfamilie'] None\n", + "inheemse eng-30-12268246-n bepaalde inheemse boom ['bepaalde inheemse boom'] ['een eeuwenoude eik']\n", + "inheemse odwn-10-109739636-n organisme met bladeren ['organisme met bladeren'] ['inheemse/uitheemse planten']\n", + "inheemse odwn-10-102422747-n soorten van vis ['soorten van vis'] ['in de Noordzee leven tweehonderdvierentwintig vissoorten', 'inheemse/uitheemse/exotische vissoorten']\n", + "inheemse eng-30-12268246-n None ['bepaalde inheemse boom'] None\n", + "inlanders odwn-10-104714918-n oorspronkelijke bewoner v.e. land ['oorspronkelijke bewoner v.e. land'] ['de tropenbossen bieden huisvesting aan miljoenen inlanders']\n", + "islamiet r_n-24303 orthodoxe islamiet [] []\n", + "islamieten eng-30-01189427-v niet eten en drinken ['niet eten en drinken'] ['tijdens de Ramadan vasten de islamieten']\n", + "jappenkamp r_n-18442 concentratiekamp van Japanners [] ['in een Jappenkamp']\n", + "jappenkampen r_n-38586 prostituee in Jappenkampen [] ['de zogeheten troostmeisjes werden gedwongen tot seksueel contact met Japanse soldaten']\n", + "kaffer eng-30-10410815-n lomperik ['iemand zonder manieren', 'pummel', 'stommeling', 'lomperd', 'lomperik', 'pummel', 'onbeschoft persoon', 'lomperik', 'botterik', 'zeer onbeleefd iemand', 'onhandig iemand', 'prehistorische mens', 'onbeschoft iemand', 'onbeschaafd iemand', 'onbeschaafd iemand', 'onbeschoft iemand'] ['Wat een kaffer is dat!']\n", + "knecht odwn-10-109860771-n knecht ['knecht'] []\n", + "knecht eng-30-10506544-n knecht van boer ['knecht van boer'] []\n", + "knecht r_n-33979 knecht v.d. slager [] []\n", + "knecht eng-30-10506544-n None ['knecht van boer'] None\n", + "knecht odwn-10-109860771-n None ['knecht'] None\n", + "knechten eng-30-09815790-n helper ['dienaar', 'helper', 'iemand die een ander helpt'] ['In de Tour werd Indurain door zijn knechten in zijn ploeg geholpen']\n", + "knechten eng-30-02496816-v onderdrukken ['beteugelen', 'intimideren', 'onderdrukken', 'onder je gezag brengen'] ['sommige graven waren ware potentaten, die de bevolking in hun graafschap met harde hand knechtten', 'de bevolking knechten']\n", + "mohammedaan r_n-24307 vrouwelijke mohammedaan [] []\n", + "mohammedaan odwn-10-107075238-n mohammedaan ['mohammedaan'] []\n", + "mohammedaan odwn-10-107075238-n None ['mohammedaan'] None\n", + "mohammedanen eng-30-03788195-n kerk v.d. mohammedanen ['kerk v.d. mohammedanen'] []\n", + "mohammedanen eng-30-03788195-n None ['kerk v.d. mohammedanen'] None\n", + "moren odwn-10-102610292-n Noordafrikaanse moslim ['Noordafrikaanse moslim'] ['De Moren veroverden Corsica in de negende eeuw.']\n", + "neger eng-30-09638009-n neger ['iemand met een donkere huidskleur', 'iemand met donkere huidskleur', 'vrouw met donkere huidskleur', 'neger', 'neger of vies persoon', 'duivel'] ['vuile nikker!']\n", + "neger eng-30-09638009-n neger of vies persoon ['iemand met een donkere huidskleur', 'iemand met donkere huidskleur', 'vrouw met donkere huidskleur', 'neger', 'neger of vies persoon', 'duivel'] []\n", + "neger eng-30-09638009-n None ['iemand met een donkere huidskleur', 'iemand met donkere huidskleur', 'vrouw met donkere huidskleur', 'neger', 'neger of vies persoon', 'duivel'] None\n", + "neger eng-30-09638009-n None ['iemand met een donkere huidskleur', 'iemand met donkere huidskleur', 'vrouw met donkere huidskleur', 'neger', 'neger of vies persoon', 'duivel'] None\n", + "negers odwn-10-101064198-n muzieksoort ontstaan bij negers ['muzieksoort ontstaan bij negers'] []\n", + "negers odwn-10-106512680-n muzieksoort ontstaan bij negers ['muzieksoort ontstaan bij negers'] []\n", + "negers r_n-35060 geestelijk lied van negers [] []\n", + "negers eng-30-06201908-n ongegronde (negatieve) mening ['vooringenomenheid', 'partijdigheid', 'ongegronde (negatieve) mening'] ['het vooroordeel dat [negers van feesten houden]', 'zonder vooroordelen', 'een vooroordeel hebben', 'de meeste mensen ontkennen dat ze vooroordelen over buitenlanders hebben', 'vooroordelen over [vreemdelingen/buitenlanders]']\n", + "negers odwn-10-106512680-n None ['muzieksoort ontstaan bij negers'] None\n", + "negers odwn-10-101064198-n None ['muzieksoort ontstaan bij negers'] None\n", + "ontdekken odwn-10-105383688-n bewoordingen die bewijs leveren ['bewoordingen die bewijs leveren'] ['bewijsplaatsen vinden/ontdekken']\n", + "ontdekken odwn-10-102951676-v opnieuw ontdekken ['opnieuw ontdekken'] ['een schilderij herontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-00721437-v vinden wat verborgen is ['vinden wat verborgen is'] ['wetenschappers vermoeden een tot op heden geheel onbekend zonnestelsel ontdekt te hebben', 'een tot op heden onbekend zonnestelsel ontdekken', 'Pierre en Marie Curie ontdekten het radium', 'het radium ontdekken', 'een fout ontdekken in een tekst', 'ontdekken dat hij spioneert', 'heb je al kunnen ontdekken of er een andere uitweg is?', 'ontdekken of er een uitweg is', 'ontdekken waarom een apparaat niet werkt', 'ontdekken dat de wereld niet vlak maar rond was', 'bij toeval de oorzaak van kraamvrouwenkoorts ontdekken']\n", + "ontdekken eng-30-04767347-n vast tijdschema voor gebeurtenissen ['vast tijdschema voor gebeurtenissen'] ['hier heerst een vaste regelmaat', 'ik probeer regelmaat in haar gedrag te ontdekken', 'ergens regelmaat in ontdekken', 'met (voldoende) regelmaat']\n", + "ontdekken eng-30-04767347-n vast tijdschema voor gebeurtenissen ['vast tijdschema voor gebeurtenissen'] ['hier heerst een vaste regelmaat', 'ik probeer regelmaat in haar gedrag te ontdekken', 'ergens regelmaat in ontdekken', 'met (voldoende) regelmaat']\n", + "ontdekken eng-30-09460312-n afdruk v.e. poot, voet, wiel op de grond ['afdruk v.e. poot, voet, wiel op de grond'] ['geen spoor meer van iets kunnen ontdekken', 'er was geen spoor van hem te bekennen', 'een spoortje [ironie/licht]', 'sporen van geweldpleging', 'zonder ook maar een spoor van ongeduld bleef hij de vragen beantwoorden', 'een spoor van ongeduld', 'iemand/iets op het spoor komen', 'het spoor bijster zijn', 'uit het spoor raken', 'sporen uitwissen', 'iemands spoor volgen', 'een spoor(tje) (van) [ironie/spot] vertonen']\n", + "ontdekken eng-30-00076196-n fout in taalgebruik ['fout in taalgebruik'] ['deze brief bevat zoveel taalfouten dat ik hem terzijde heb gelegd', 'een taalfout verbeteren', 'een taalfout ontdekken', 'een taalfout maken']\n", + "ontdekken eng-30-02154508-v na zoeken ontdekken ['na zoeken ontdekken'] ['de gevluchte inbreker vinden onder de brug', 'de weg niet kunnen vinden', 'iemand bereid vinden om iets (voor je) te doen', 'een man/baan/huis vinden', 'ik zoek al dagen naar dat rapport, maar het is nergens te vinden', 'nergens te vinden zijn']\n", + "ontdekken r_n-40901 het ontdekken [] ['de vinding van een schat']\n", + "ontdekken eng-30-02154508-v None ['na zoeken ontdekken'] None\n", + "ontdekken odwn-10-102951676-v None ['opnieuw ontdekken'] None\n", + "ontwikkelingsland odwn-10-100905185-v mensen sturen ['mensen sturen'] ['iemand als arts naar een ontwikkelingsland uitzenden']\n", + "ontwikkelingslanden eng-30-08195636-n hulp aan ontwikkelingslanden ['hulp aan ontwikkelingslanden', 'hulp aan ontwikkelingslanden'] ['de ontwikkelingshulp bevriezen', 'ontwikkelingshulp aan [Somalië]', 'ontwikkelingshulp geven/verstrekken (aan een land)', 'ontwikkelingshulp krijgen']\n", + "ontwikkelingslanden odwn-10-107793684-n land met weinig (economische) groei ['land met weinig (economische) groei'] ['in de ontwikkelingslanden']\n", + "ontwikkelingslanden eng-30-08195636-n hulp aan ontwikkelingslanden ['hulp aan ontwikkelingslanden', 'hulp aan ontwikkelingslanden'] []\n", + "ontwikkelingslanden odwn-10-108219147-n internationale handel ['internationale handel'] ['de organisatie ziet vooral ontwikkelingslanden profiteren van de toenemende vrije wereldhandel', 'de vrije wereldhandel']\n", + "ontwikkelingslanden odwn-10-108533146-n winkel die ontwikkelingslanden steunt ['winkel die ontwikkelingslanden steunt'] []\n", + "ontwikkelingslanden eng-30-08195636-n None ['hulp aan ontwikkelingslanden', 'hulp aan ontwikkelingslanden'] None\n", + "ontwikkelingslanden eng-30-08195636-n None ['hulp aan ontwikkelingslanden', 'hulp aan ontwikkelingslanden'] None\n", + "ontwikkelingslanden odwn-10-108533146-n None ['winkel die ontwikkelingslanden steunt'] None\n", + "politionele acties eng-30-01080366-n manifestatie ['manifestatie'] ['de acties zullen een publieksvriendelijk karakter hebben', 'een actie tegen de aanleg van de Betuwelijn', 'een actie tegen [iets/iemand]', 'actie voeren', 'de boeren dreigen met harde acties', 'harde actie', 'de politionele acties', 'acties afkondigen (tegen het regeringsbeleid)', 'tot actie oproepen', 'acties staken/afblazen/beëindigen/opschorten', 'acties organiseren']\n", + "primitief eng-30-02932400-n primitief huisje ['primitief huisje'] ['lemen/rieten/houten hutten', 'die mensen wonen in hutten', 'in een hut', 'de kinderen hadden een hut in de tuin gebouwd', 'een hut bouwen']\n", + "primitief eng-30-10553402-n primitief iemand ['woesteling', 'bloeddorstig persoon', 'natuurliefhebber', 'primitief iemand'] [\"Rousseau's idee van de 'edele wilde' is toch wel achterhaald\"]\n", + "primitief eng-30-01558993-n None ['primitief bankbiljet'] None\n", + "primitief eng-30-10553402-n None ['woesteling', 'bloeddorstig persoon', 'natuurliefhebber', 'primitief iemand'] None\n", + "primitief eng-30-02932400-n None ['primitief huisje'] None\n", + "primitieve eng-30-00910203-n opname van geluid ['opname van geluid', 'het maken v.e. film, foto, geluidsband', 'opname van beeld of geluid'] ['geluidsopnamen maken van primitieve muziek']\n", + "primitieve eng-30-09627462-n iemand die schildert in primitieve stijl ['iemand die schildert in primitieve stijl'] []\n", + "primitieve eng-30-09627462-n None ['iemand die schildert in primitieve stijl'] None\n", + "pygmeeën eng-30-09183693-n algemene gewoonte of gebruik ['opvatting over goed en slecht', 'zienswijze bepaald door moraal', 'algemene gewoonte of gebruik', 'ethische normen en regels'] ['zeden en gewoonten (van de Pygmeeën)']\n", + "ras odwn-10-108984511-n ras van mensen met een bepaalde huidskleur ['ras van mensen met een bepaalde huidskleur'] ['Het maakt niet uit van welke kleur je bent. We nemen iedereen aan.', 'Iemand van een kleur']\n", + "ras eng-30-10502950-n iemand die mensen v.e. ander ras haat ['iemand die mensen v.e. ander ras haat'] ['ze schold hem uit voor racist']\n", + "ras odwn-10-100937974-n mensenras ['mensenras'] ['het menselijke ras']\n", + "ras eng-30-07967382-n type mensen ['type mensen'] ['een ras van zeevaarders']\n", + "ras eng-30-14410918-n probleem vanwege verschillen in ras ['probleem vanwege verschillen in ras', 'probleem vanwege verschillen in ras'] ['de pijnlijke rassenkwestie in de V.S.']\n", + "ras odwn-10-104772963-n gescheiden samenleving obv. ras ['gescheiden samenleving obv. ras'] ['in Zuid-Afrika werd jarenlang een politiek van rassenscheiding gevoerd']\n", + "ras eng-30-14410918-n probleem vanwege verschillen in ras ['probleem vanwege verschillen in ras', 'probleem vanwege verschillen in ras'] []\n", + "ras odwn-10-108984511-n None ['ras van mensen met een bepaalde huidskleur'] None\n", + "ras odwn-10-104772963-n None ['gescheiden samenleving obv. ras'] None\n", + "ras eng-30-10502950-n None ['iemand die mensen v.e. ander ras haat'] None\n", + "ras eng-30-14410918-n None ['probleem vanwege verschillen in ras', 'probleem vanwege verschillen in ras'] None\n", + "ras eng-30-14410918-n None ['probleem vanwege verschillen in ras', 'probleem vanwege verschillen in ras'] None\n", + "rassen eng-30-10157549-n kind van verschillende rassen ['persoon van gemengde afkomst', 'kind van verschillende rassen'] ['zwarten, blanken en kleurlingen']\n", + "rassen eng-30-00850425-n voortplanting door verschillende rassen ['voortplanting door verschillende rassen', 'kruising'] ['een kruising tussen/van [een teckel en een terriër]']\n", + "rassen eng-30-01155044-n haat jegens andere rassen ['haat jegens andere rassen', 'discriminatie op basis van ras', 'haat op basis van verschil in ras'] ['Er werd een demonstratie gehouden tegen het opkomend racisme']\n", + "rassen odwn-10-107524753-v gemengd raken ['gemengd raken'] ['die rassen vermengen zich', 'water vermengt zich niet met olie', 'zich met olie vermengen']\n", + "rassen eng-30-10157549-n None ['persoon van gemengde afkomst', 'kind van verschillende rassen'] None\n", + "rassen eng-30-01155044-n None ['haat jegens andere rassen', 'discriminatie op basis van ras', 'haat op basis van verschil in ras'] None\n", + "rassen eng-30-00850425-n None ['voortplanting door verschillende rassen', 'kruising'] None\n", + "slaaf eng-30-10609325-n iemand die eigendom is v.e. ander ['iemand die eigendom is v.e. ander', 'iemand die eigendom is v.e. ander'] ['iemand tot slaaf maken']\n", + "slaaf eng-30-09976551-n v.e. ander afhankelijk persoon ['v.e. ander afhankelijk persoon', 'uitgebuite vrouw'] ['Ik ben je slaaf niet!', 'Ik ben je slaaf niet!']\n", + "slaaf eng-30-09976551-n v.e. ander afhankelijk persoon ['v.e. ander afhankelijk persoon', 'uitgebuite vrouw'] ['Ik ben je slaaf niet!', 'Ik ben je slaaf niet!']\n", + "slaaf eng-30-13997253-n toestand van slaaf zijn ['slavernij', 'toestand van slaaf zijn'] ['de slavernij is afgeschaft', 'iemand uit de slavernij verlossen', 'iemand in slavernij brengen']\n", + "slaaf eng-30-10580535-n None ['iemand die bezit was v.e. landeigenaar', 'slaaf'] None\n", + "slaaf eng-30-13997253-n None ['slavernij', 'toestand van slaaf zijn'] None\n", + "slaven odwn-10-109472945-n toekenning van gelijke rechten ['toekenning van gelijke rechten'] ['de emancipatie van de slaven in de 19e eeuw', \"de emancipatie van de vrouw/ouderen/homo's\"]\n", + "slaven eng-30-00623545-n werk verricht door slaven ['werk verricht door slaven'] []\n", + "slaven eng-30-01114284-n handel in slaven ['handel in slaven'] []\n", + "slaven eng-30-02256998-v loskopen ['loskopen'] ['slaven/gevangenen vrijkopen']\n", + "slaven eng-30-00623545-n None ['werk verricht door slaven'] None\n", + "slaven eng-30-01114284-n None ['handel in slaven'] None\n", + "stam eng-30-13164763-n nieuw uitgelopen tak aan een plant/boom ['nieuw uitgelopen twijg', 'nieuw uitgelopen tak aan een plant/boom', 'nieuw uitgelopen twijg', 'stekje, loot, jonge boom', 'uitgelopen tak', 'nieuw takje', 'nieuw uitgelopen twijg', 'jonge bladstengel', 'jonge boom', 'nieuwe aangroei bij planten'] ['een nieuwe/jonge loot aan de [politieke] stam', 'het Nederlands en het Gotisch zijn loten van dezelfde stam', 'er komen nieuwe loten aan']\n", + "stam eng-30-13164763-n nieuw uitgelopen tak aan een plant/boom ['nieuw uitgelopen twijg', 'nieuw uitgelopen tak aan een plant/boom', 'nieuw uitgelopen twijg', 'stekje, loot, jonge boom', 'uitgelopen tak', 'nieuw takje', 'nieuw uitgelopen twijg', 'jonge bladstengel', 'jonge boom', 'nieuwe aangroei bij planten'] ['een nieuwe/jonge loot aan de [politieke] stam', 'het Nederlands en het Gotisch zijn loten van dezelfde stam', 'er komen nieuwe loten aan']\n", + "stam eng-30-06320569-n woordsoort voor handeling/staat/proces ['werkwoord', 'woordsoort voor handeling/staat/proces'] ['de stam van een werkwoord', 'wederkerende werkwoorden', 'een scheidbaar samengesteld werkwoord', 'regelmatige/onregelmatige werkwoorden', 'de modale werkwoorden', 'een reflexief werkwoord', 'onovergankelijke/intransitieve werkwoorden', 'zwakke/sterke werkwoorden', 'overgankelijke/transitieve werkwoorden', 'een werkwoord vervoegen']\n", + "stam eng-30-12731714-n None ['loofboom met een rechte stam'] None\n", + "stammen eng-30-00251791-v oorsprong ontlenen ['oorsprong ontlenen'] ['veel hedendaagse rituelen stammen van oeroude gebruiken af', 'van gebruiken afstammen']\n", + "stammen eng-30-07970721-n mensen met gemeenschappelijke afkomst ['verzameling van bloedverwanten', 'mensen met gemeenschappelijke afkomst', 'geslacht van mensen', 'familietak', 'alle mensen van één geslacht', 'deel v.e. familie'] ['het geslacht van de Bourbons', 'stammen uit een nobel/adellijk geslacht', 'van een voornaam geslacht', 'tot een rijk/adellijk/aanzienlijk/oud geslacht behoren']\n", + "stammen r_v-4063 mensen onderwerpen [] ['stammen koloniseren']\n", + "stammen eng-30-07969695-n groep mensen ['volksstam met eigen gewoonten en een eigen gebied', 'groep mensen', 'groep mensen met dezelfde voorvaders'] ['een lokale stam', 'nomadische stammen']\n", + "stammen eng-30-07970721-n alle mensen van één geslacht ['verzameling van bloedverwanten', 'mensen met gemeenschappelijke afkomst', 'geslacht van mensen', 'familietak', 'alle mensen van één geslacht', 'deel v.e. familie'] ['de twaalf stammen van Israël']\n", + "stammen eng-30-02624263-v afkomstig zijn van ['voortspruiten', 'ontstaan', 'ontstaan', 'opschieten', 'afkomstig zijn van', 'ontkiemen', 'zich vasthechten'] ['het oude gebruik stamt uit de tijd van Napoleon', 'uit een tijd/taal/streek/geslacht stammen', 'stammen van een [woord/familie]']\n", + "stammen eng-30-02624263-v afkomstig zijn van ['voortspruiten', 'ontstaan', 'ontstaan', 'opschieten', 'afkomstig zijn van', 'ontkiemen', 'zich vasthechten'] ['het oude gebruik stamt uit de tijd van Napoleon', 'uit een tijd/taal/streek/geslacht stammen', 'stammen van een [woord/familie]']\n", + "stammen odwn-10-102673566-n oorlog tussen stammen ['oorlog tussen stammen'] ['de stammenoorlog in dat Afrikaanse land blijft slachtoffers eisen']\n", + "stammen eng-30-01236947-n langdurige ruzie tussen (veel) mensen ['langdurige ruzie tussen (veel) mensen'] ['er woedt al jarenlang een bloedige vete tussen het ANC en Inkatha', 'er woedt een vete', 'zij moeten hun onderling vetes maar zonder mij uitvechten', 'onderlinge vetes uitvechten', 'een vete met [de buren]', 'de oude veten tussen de twee stammen zal de komende tijd niet opgelost worden.', 'een (oude) vete tussen [mensen]']\n", + "stammen odwn-10-102673566-n None ['oorlog tussen stammen'] None\n", + "trans r_n-12184 zeer lange tijd [] ['de eindeloosheid van een reis met de Trans-Siberische spoorlijn']\n", + "westers odwn-10-108925479-n overmacht v.h. geld ['overmacht v.h. geld'] ['de macht van het kapitalisme', '[een marionet van] Westers kapitalisme']\n", + "westers r_v-9494 westers worden [] ['deze Aziatische stad is al sterk verwesterd']\n", + "westerse r_n-10214 geschiedenis v.d. cultuur [] ['de westerse cultuurgeschiedenis']\n", + "westerse eng-30-08366753-n de economische praktijk ['de economische praktijk'] ['de Westerse/Russische/regionale economie', 'de tegenstelling tussen economie en milieu', 'een veerkrachtige economie', \"de economie groeit/'trekt aan'\", 'geleide economie', 'een derdewereldland met een noodlijdende economie', 'een noodlijdende economie', 'een geïndustrialiseerd land met een gezonde economie', 'een gezonde economie', 'de handelsbalans en het aardgas zijn de vitale segmenten van de Nederlandse economie', 'segmenten/sectoren van de economie', 'de hoge loonkosten ontwrichten de Nederlandse economie', 'de economie ontwrichten', 'een gesloten economie', 'een open economie', 'een stagnerende economie', 'een oplevende/aantrekkende economie']\n", + "westerse eng-30-05793554-n grondslag of basis van iets ['uitgangspunt', 'grondslag of basis van iets', 'grondslag of beginselen waarop iets berust', 'fundamenten waarop wordt gebouwd', 'basis', 'datgene waarop iets berust', 'grondslag', 'grondslag'] ['de fundamenten van de westerse samenleving', 'het fundament van', 'het financiële fundament voor een ingreep in de sociale zekerheid', 'het fundament voor iets', 'het Christendom is een stevig fundament onder onze maatschappij', 'een stevig fundament', 'vader Drees heeft de fundamenten van de verzorgingsstaat gelegd', 'de fundamenten leggen']\n", + "westerse r_v-2880 van personen [] ['hij gedijt niet goed in de westerse maatschappij', 'goed/slecht/niet gedijen']\n", + "westerse odwn-10-105865991-n land met veel industrie ['land met veel industrie'] ['de westerse industrielanden', 'de leiders van de zeven rijkste industrielanden (G-7) kwamen in Washington bijeen', 'de zeven grootste/rijkste industrielanden']\n", + "westerse eng-30-07966140-n maatschappij ['groep personen', 'samenleving', 'maatschappij', 'samenleving'] ['de moderne/westerse samenleving']\n", + "westerse odwn-10-100529782-n geijkt patroon ['geijkt patroon'] ['de verwerping van Westerse politieke sjablonen']\n", + "westerse eng-30-13941469-n hoogte v.d. welvaart ['materieel niveau v.h. leven', 'kosten om te leven', 'hoogte v.d. welvaart'] ['een laag welvaartspeil', 'de westerse landen hebben een hoog welvaartspeil', 'een hoog welvaartspeil', 'het welvaartspeil stijgt']\n", + "wit r_n-43414 taal in Wit-Rusland [] []\n", + "wit eng-30-02133435-v als uiterlijk hebben ['een bepaald uiterlijk hebben', 'gezicht vertonen', 'eruitzien', 'staan (van kleding)', 'mooi passen', 'een indruk geven', 'als uiterlijk hebben'] ['het ziet (er) zwart van de mensen', 'je ziet wat bleek, is er wat?', 'wit/bleek zien']\n", + "wit eng-30-09921409-n None ['al te goed persoon', 'goedige vent', 'bepaalde wit-met-grijze vogel'] None\n", + "witte odwn-10-105591402-n lichte plek bij dieren ['lichte plek bij dieren'] ['een zwarte kat met een witte bef']\n", + "witte odwn-10-102601580-n mensen met bepaalde taak ['mensen met bepaalde taak'] ['de Witte Brigade', 'de Luchtmobiele Brigade']\n", + "witte eng-30-09873899-n iemand die dieren fokt ['iemand die dieren fokt'] ['een fokker van witte geiten']\n", + "witte eng-30-14649197-n chemisch element ['chemisch element'] ['het gehalte aan fosfor bepalen', 'elementair fosfor', 'witte/rode fosfor']\n", + "witte eng-30-09762509-n iemand die iets goed kan ['iem. die uitblinkt', 'iemand die goed leert', 'iemand die uitblinkt', 'iemand die uitblinkt in bv. sport', 'iemand die ongelooflijke dingen kan', 'uitblinker', 'zeer begaafd iemand', 'toonaangevend iemand op bepaald gebied', 'erg intelligent persoon', 'persoon of ploeg die het beste is', 'iemand die ergens in uitmunt', 'iemand erg goed ergens in', 'iemand met inzicht en kennis', 'iemand die ergens erg goed in is', 'iem. die uitzonderlijk begaafd is', 'iemand die iets goed kan', 'op enige wijze opvallend iemand', 'iemand die ergens in uitblinkt', 'iemand die kan toveren', 'slim iemand', 'uitblinker m.n. in de muziek'] ['een meester zijn in [het bedenken van uitvluchten]', 'hij is een meester op de viool', 'een meester zijn op [een muziekinstrument]', 'meesters van [het witte doek/de schilderkunst]']\n", + "witte eng-30-07687053-n papierachtige eetbare substantie ['soort vanillewafeltje', 'papierachtige eetbare substantie'] ['witte ouwel']\n", + "witte r_n-44471 bepaald plantengeslacht [] ['gewone/witte zuring']\n", + "zigeuners odwn-10-100857451-v een slechte naam bezorgen ['een slechte naam bezorgen'] ['zigeuners werden in het verleden al gauw gebrandmerkt als dieven', 'iemand brandmerken als dief', 'de televisie brandmerken als de grote boosdoener']\n", + "zigeuners eng-30-10154186-n lid v.e. rondtrekkend volk ['lid v.e. rondtrekkend volk'] ['er uitzien als een zigeuner', 'hij is een echte zigeuner', 'een kamp/standplaats van zigeuners']\n", + "zigeuners odwn-10-107418910-n muziek typisch van zigeuners ['muziek typisch van zigeuners'] []\n", + "zigeuners odwn-10-103179139-n alle zigeuners samen ['alle zigeuners samen'] []\n", + "zigeuners odwn-10-107418910-n None ['muziek typisch van zigeuners'] None\n", + "zigeuners odwn-10-103179139-n None ['alle zigeuners samen'] None\n", + "zwart eng-30-01893825-n zwart diertje dat onder de grond leeft ['klein zoogdier met stekels', 'zwart diertje dat onder de grond leeft', 'Afrikaans knaagdier met stekels'] []\n", + "zwart odwn-10-105801592-n dier dat helemaal zwart is ['dier dat helemaal zwart is'] []\n", + "zwart eng-30-02133435-v als uiterlijk hebben ['een bepaald uiterlijk hebben', 'gezicht vertonen', 'eruitzien', 'staan (van kleding)', 'mooi passen', 'een indruk geven', 'als uiterlijk hebben'] ['het ziet (er) zwart van de mensen', 'je ziet wat bleek, is er wat?', 'wit/bleek zien']\n", + "zwart eng-30-01893825-n None ['klein zoogdier met stekels', 'zwart diertje dat onder de grond leeft', 'Afrikaans knaagdier met stekels'] None\n", + "zwart odwn-10-105801592-n None ['dier dat helemaal zwart is'] None\n", + "zwarte odwn-10-105591402-n lichte plek bij dieren ['lichte plek bij dieren'] ['een zwarte kat met een witte bef']\n", + "zwarte odwn-10-108091031-n grote zwarte of witte zwemvogel ['grote zwarte of witte zwemvogel'] ['de wilde/gewone/zwarte/Australische zwaan']\n", + "zwarte odwn-10-108091031-n grote zwarte of witte zwemvogel ['grote zwarte of witte zwemvogel'] ['de wilde/gewone/zwarte/Australische zwaan']\n", + "zwarte eng-30-09859038-n aanhanger v.h. fascisme ['aanhanger v.h. fascisme'] ['zijn vader was een zwarte']\n", + "zwarte odwn-10-108091031-n None ['grote zwarte of witte zwemvogel'] None\n", + "zwarten odwn-10-103541331-n iemand met lichte huidskleur ['iemand met lichte huidskleur'] ['blanken en zwarten worden in Zuid-Afrika niet langer apart gehouden', 'onder de apartheid hadden blanken meer rechten dan zwarten']\n", + "zwarten odwn-10-103541331-n iemand met lichte huidskleur ['iemand met lichte huidskleur'] ['blanken en zwarten worden in Zuid-Afrika niet langer apart gehouden', 'onder de apartheid hadden blanken meer rechten dan zwarten']\n", + "zwarten eng-30-10157549-n kind van verschillende rassen ['persoon van gemengde afkomst', 'kind van verschillende rassen'] ['zwarten, blanken en kleurlingen']\n" + ] + } + ], + "source": [ + "# sense_definition, synset_definitions, sense_examples\n", + "case_4 = []\n", + "case_4_count = 0\n", + "\n", + "for term, hits in odwn_subset.items():\n", + " for hit in hits:\n", + " \n", + " # get odwn ID\n", + " if hit[\"synset_id\"] != \"\":\n", + " odwn_id_key = \"synset_id\"\n", + " else:\n", + " odwn_id_key = \"sense_id\"\n", + " \n", + " if hit[\"found_in\"] == \"sense_definition\" or hit[\"found_in\"] == \"synset_definitions\" \\\n", + " or hit[\"found_in\"] == \"sense_examples\":\n", + " case_4_count += 1\n", + " case_4.append(hit[odwn_id_key])\n", + " print(term, hit[odwn_id_key], hit.get(\"sense_definition\"),hit.get(\"synset_definitions\"),hit.get(\"sense_examples\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "303" + ] + }, + "execution_count": 58, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_4_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/odwn_case4.txt','w') as txt_file:\n", + " for l in case_4:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Case 5" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "aboriginal odwn-10-101180571-n aboriginal\n", + "achterlijke eng-30-09921409-n achterlijke\n", + "achterlijkheid eng-30-05646218-n achterlijkheid\n", + "achterlijkheid achterlijkheid\n", + "afkomst eng-30-06009086-n afkomst\n", + "afkomst eng-30-08510456-n afkomst\n", + "afkomst eng-30-04923743-n afkomst\n", + "allochtoon eng-30-09484465-n allochtoon\n", + "baboe odwn-10-106744972-n baboe\n", + "barbaar eng-30-10390902-n barbaar\n", + "bediende eng-30-10053808-n bediende\n", + "bediende eng-30-10582154-n bediende\n", + "berber odwn-10-101847342-n Berber\n", + "berbers Berbers\n", + "birma eng-30-08715390-n Birma\n", + "birma Birma\n", + "blanke odwn-10-103541331-n blanke\n", + "bosneger odwn-10-103272943-n bosneger\n", + "eskimo eng-30-06918215-n Eskimo\n", + "etniciteit eng-30-04799133-n etniciteit\n", + "gay eng-30-10182913-n gay\n", + "halfbloed eng-30-01327322-n halfbloed\n", + "halfbloed eng-30-10157378-n halfbloed\n", + "halfbloed eng-30-10157549-n halfbloed\n", + "handicap eng-30-14548343-n handicap\n", + "handicap odwn-10-101168606-n handicap\n", + "handicap eng-30-14052403-n handicap\n", + "handicap eng-30-05689249-n handicap\n", + "handicap handicap\n", + "hermafrodiet eng-30-10172080-n hermafrodiet\n", + "hermafrodiet odwn-10-108184026-n hermafrodiet\n", + "homo homo\n", + "homoseksualiteit eng-30-00858060-n homoseksualiteit\n", + "homoseksuele eng-30-10182913-n homoseksuele\n", + "inboorling odwn-10-103586613-n inboorling\n", + "indiaan odwn-10-106518418-n Indiaan\n", + "inuit Inuit\n", + "islamiet odwn-10-100569798-n islamiet\n", + "jappenkamp jappenkamp\n", + "kaukasische Kaukasische\n", + "knecht eng-30-10292192-n knecht\n", + "knecht eng-30-10308938-n knecht\n", + "knechten eng-30-02496816-v knechten\n", + "koelie odwn-10-101160806-n koelie\n", + "koppensneller eng-30-10163452-n koppensneller\n", + "medicijnman eng-30-10626439-n medicijnman\n", + "mesties odwn-10-100513750-n mesties\n", + "mohammedaan odwn-10-107525787-n mohammedaan\n", + "mongools odwn-10-106363474-n Mongools\n", + "moor eng-30-09636339-n moor\n", + "moor odwn-10-105801592-n moor\n", + "mulat eng-30-09638454-n mulat\n", + "mulat odwn-10-106536961-n mulat\n", + "neger eng-30-09636339-n neger\n", + "ontdekken eng-30-02154508-v ontdekken\n", + "ontdekken eng-30-02128066-v ontdekken\n", + "ontdekken eng-30-00721437-v ontdekken\n", + "ontdekken odwn-10-108767604-v ontdekken\n", + "ontwikkelingsland eng-30-08167046-n ontwikkelingsland\n", + "page eng-30-10391086-n page\n", + "page page\n", + "ras odwn-10-100937974-n ras\n", + "ras eng-30-07967382-n ras\n", + "slaaf eng-30-10609325-n slaaf\n", + "slaaf eng-30-09976551-n slaaf\n", + "slaaf odwn-10-107447736-n slaaf\n", + "slaven slaven\n", + "stammen eng-30-02624263-v stammen\n", + "trans trans\n", + "trans trans\n", + "travestiet eng-30-10726031-n travestiet\n", + "zwarte eng-30-09636339-n zwarte\n" + ] + } + ], + "source": [ + "# lemmas no markers\n", + "case_5 = []\n", + "case_5_count = 0\n", + "for term, hits in odwn_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"le\":\n", + " \n", + " # get odwn ID\n", + " if hit[\"synset_id\"] != \"\":\n", + " odwn_id_key = \"synset_id\"\n", + " else:\n", + " odwn_id_key = \"sense_id\"\n", + " \n", + " # no markers\n", + " if hit[odwn_id_key] not in odwn_implicit and hit[odwn_id_key] not in odwn_explicit:\n", + " case_5_count += 1\n", + " case_5.append(hit[odwn_id_key])\n", + " print(term, hit[\"synset_id\"], hit[\"le_written_form\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "72" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_5_count" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/odwn_case5.txt','w') as txt_file:\n", + " for l in case_5:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "barbaar eng-30-10410815-n barbaar\n", + "barbaar eng-30-09879297-n barbaar\n", + "dwerg eng-30-10040344-n dwerg\n", + "homoseksualiteit eng-30-00856847-n homoseksualiteit\n", + "jap odwn-10-103201483-n Jap\n", + "kaffer eng-30-10410815-n kaffer\n", + "kaffer odwn-10-100082478-n kaffer\n", + "koelie eng-30-10035809-n koelie\n", + "lilliputter eng-30-10040344-n lilliputter\n", + "mongool eng-30-10197525-n mongool\n", + "moor eng-30-09638009-n moor\n", + "neger eng-30-09638009-n neger\n", + "zwarte eng-30-09638009-n zwarte\n", + "zwarte eng-30-09859038-n zwarte\n" + ] + } + ], + "source": [ + "# lemmas with markers\n", + "case_5_markers = []\n", + "case_5_markers_count = 0\n", + "for term, hits in odwn_subset.items():\n", + " for hit in hits:\n", + " if hit[\"found_in\"] == \"le\":\n", + " \n", + " # get odwn ID\n", + " if hit[\"synset_id\"] != \"\":\n", + " odwn_id_key = \"synset_id\"\n", + " else:\n", + " odwn_id_key = \"sense_id\"\n", + " \n", + " # no markers\n", + " if hit[odwn_id_key] in odwn_implicit or hit[odwn_id_key] in odwn_explicit:\n", + " case_5_markers_count += 1\n", + " case_5_markers.append(hit[odwn_id_key])\n", + " print(term, hit[odwn_id_key], hit[\"le_written_form\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "14" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "case_5_markers_count" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [], + "source": [ + "# export\n", + "with open('selected_cases/odwn_case5_with_markers.txt','w') as txt_file:\n", + " for l in case_5_markers:\n", + " txt_file.write(f\"{l}\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.5" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/sensitivity_markers/selected_cases/aat_en_case1.txt b/sensitivity_markers/selected_cases/aat_en_case1.txt new file mode 100644 index 0000000..1e43cc8 --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_en_case1.txt @@ -0,0 +1,45 @@ +300012925 +300449148 +300435249 +300378963 +300244538 +300244674 +300244539 +300244536 +300244540 +300411945 +300041590 +300386950 +300016731 +300016736 +300411929 +300435249 +300250435 +300391091 +300265711 +300435115 +300435114 +300025844 +300018863 +300379660 +300102550 +300017458 +300417391 +300311173 +300265512 +300386886 +300393224 +300055033 +300056548 +300262942 +300262938 +300014934 +300435318 +300136452 +300411753 +300419276 +300435679 +300022218 +300411958 +300049946 +300129784 diff --git a/sensitivity_markers/selected_cases/aat_en_case1_with_markers.txt b/sensitivity_markers/selected_cases/aat_en_case1_with_markers.txt new file mode 100644 index 0000000..a93d9f9 --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_en_case1_with_markers.txt @@ -0,0 +1,13 @@ +300025925 +300017447 +300386060 +300310690 +300443480 +300386794 +300017455 +300443390 +300017437 +300056460 +300056500 +300016430 +300025874 diff --git a/sensitivity_markers/selected_cases/aat_en_case2.txt b/sensitivity_markers/selected_cases/aat_en_case2.txt new file mode 100644 index 0000000..741f88c --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_en_case2.txt @@ -0,0 +1,128 @@ +300379660 +300404576 +300106913 +300018585 +300018585 +300018585 +300012925 +300012925 +300263729 +300375152 +300449148 +300443479 +300443479 +300378963 +300375341 +300012439 +300244538 +300244538 +300244539 +300244539 +300244540 +300244540 +300379994 +300025924 +300025926 +300000311 +300000311 +300025921 +300025921 +300375533 +300266100 +300041590 +300041590 +300041590 +300041590 +300041590 +300041590 +300041590 +300386950 +300386950 +300236748 +300016731 +300016731 +300016736 +300016736 +300102550 +300102550 +300102489 +300102489 +300102489 +300102489 +300411929 +300191997 +300197770 +300250435 +300400510 +300400510 +300391091 +300391091 +300391091 +300400507 +300055188 +300199725 +300199725 +300404070 +300195349 +300233041 +300265711 +300400507 +300400507 +300055188 +300055188 +300435114 +300025844 +300017650 +300379660 +300379660 +300379660 +300379660 +300102579 +300102550 +300265652 +300265652 +300265652 +300375528 +300218522 +300018103 +300073715 +300375152 +300018125 +300121558 +300121558 +300393224 +300393224 +300375194 +300375194 +300374845 +300018279 +300185762 +300055033 +300055033 +300019021 +300174254 +300056548 +300262937 +300262937 +300389910 +300100810 +300055188 +300417371 +300256475 +300256475 +300014934 +300014934 +300136452 +300411753 +300113288 +300113288 +300419276 +300419276 +300419276 +300379994 +300435679 +300435679 +300417823 +300022218 +300411958 +300400510 diff --git a/sensitivity_markers/selected_cases/aat_en_case2_with_markers.txt b/sensitivity_markers/selected_cases/aat_en_case2_with_markers.txt new file mode 100644 index 0000000..fedfa3a --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_en_case2_with_markers.txt @@ -0,0 +1,27 @@ +300025925 +300310411 +300017455 +300017455 +300017447 +300449024 +300017437 +300017437 +300017437 +300386794 +300386794 +300386794 +300443390 +300017437 +300017437 +300017437 +300017437 +300056460 +300056500 +300310411 +300310411 +300016430 +300025925 +300025874 +300055309 +300230899 +300230899 diff --git a/sensitivity_markers/selected_cases/aat_en_case3.txt b/sensitivity_markers/selected_cases/aat_en_case3.txt new file mode 100644 index 0000000..30b9115 --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_en_case3.txt @@ -0,0 +1,342 @@ +300120040 +300435249 +300435341 +300198715 +300387326 +300264789 +300386485 +300438772 +300018409 +300012925 +300263397 +300263728 +300263735 +300263737 +300263738 +300263998 +300263740 +300263729 +300016595 +300375152 +300262593 +300448122 +300449148 +300020118 +300021925 +300019470 +300443479 +300400853 +300198715 +300264498 +300264320 +300417414 +300228512 +300375367 +300375431 +300022012 +300410257 +300107052 +300019089 +300410258 +300410260 +300386148 +300266481 +300018988 +300417414 +300391253 +300244538 +300244674 +300244539 +300182578 +300244540 +300244687 +300244158 +300310660 +300013583 +300264634 +300011161 +300266080 +300012482 +300013423 +300012939 +300379604 +300263717 +300264336 +300255718 +300449148 +300411617 +300016575 +300027015 +300198715 +300386015 +300264324 +300375152 +300189309 +300006719 +300343487 +300006745 +300000311 +300386051 +300391311 +300264523 +300137801 +300444006 +300054687 +300434911 +300254807 +300266100 +300386945 +300310690 +300386950 +300343714 +300263109 +300016731 +300016736 +300102489 +300411929 +300017437 +300389818 +300400856 +300055303 +300438784 +300435431 +300025929 +300054316 +300054447 +300443479 +300417373 +300449148 +300265422 +300400818 +300016281 +300435249 +300263154 +300443479 +300443481 +300263554 +300263144 +300417767 +300020935 +300265043 +300106984 +300018959 +300113602 +300263588 +300020085 +300203949 +300204022 +300449024 +300438588 +300206687 +300448847 +300233909 +300127280 +300258884 +300235117 +300036879 +300400510 +300391091 +300055475 +300404069 +300126370 +300111210 +300042168 +300232777 +300232779 +300006777 +300122943 +300389935 +300024979 +300265711 +300393250 +300265019 +300016575 +300265862 +300262962 +300108469 +300027808 +300018071 +300179506 +300210746 +300192795 +300264473 +300386028 +300017437 +300018863 +300400847 +300017596 +300016954 +300016773 +300017706 +300249545 +300262973 +300386028 +300018564 +300435341 +300380093 +300311237 +300411917 +300017583 +300438808 +300019487 +300244536 +300386793 +300386794 +300400843 +300404070 +300400847 +300400836 +300400848 +300388693 +300435741 +300438494 +300438480 +300017447 +300102550 +300017458 +300265652 +300055999 +300265171 +300265173 +300018959 +300021637 +300417391 +300053490 +300013626 +300311175 +300443390 +300435259 +300107836 +300265506 +300265512 +300017437 +300018777 +300389818 +300389501 +300250079 +300140253 +300011200 +300120786 +300298733 +300266843 +300386937 +300020944 +300198715 +300438369 +300438439 +300438364 +300438520 +300404766 +300017762 +300017437 +300018863 +300017554 +300389818 +300056460 +300438519 +300056500 +300055970 +300021521 +300022022 +300374835 +300018863 +300022024 +300252610 +300123430 +300179434 +300196838 +300417205 +300417193 +300417202 +300264330 +300055033 +300028710 +300016925 +300019289 +300019508 +300056548 +300020074 +300265683 +300264837 +300174254 +300056500 +300143666 +300016430 +300262764 +300260713 +300263793 +300264475 +300265422 +300249198 +300449021 +300443479 +300443481 +300055479 +300386795 +300233434 +300036935 +300111551 +300232853 +300233909 +300228124 +300201794 +300265774 +300235120 +300265478 +300393209 +300258978 +300435318 +300136452 +300236032 +300411753 +300448974 +300150456 +300311322 +300256825 +300198715 +300233279 +300258488 +300005675 +300417705 +300264337 +300262022 +300438466 +300193270 +300165261 +300443560 +300264839 +300438843 +300438761 +300417392 +300417391 +300417316 +300435025 +300400510 +300435504 +300435431 +300438772 +300386028 +300438515 +300017641 +300438785 +300438778 +300021877 +300263657 +300017706 +300111201 +300417400 +300312337 +300262650 +300251739 +300111207 +300111276 +300438466 +300262593 +300375176 +300249198 +300155665 +300021925 +300264340 +300431758 +300129784 +300312263 diff --git a/sensitivity_markers/selected_cases/aat_nl_case1.txt b/sensitivity_markers/selected_cases/aat_nl_case1.txt new file mode 100644 index 0000000..f2f176e --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_nl_case1.txt @@ -0,0 +1,48 @@ +300021862 +300012925 +300025874 +300379156 +300036973 +300197021 +300236748 +300134111 +300017447 +300102528 +300102572 +300411929 +300250435 +300191997 +300391091 +300025924 +300025926 +300025921 +300389935 +300310667 +300400507 +300055188 +300418042 +300379660 +300387326 +300244536 +300411945 +300244537 +300265512 +300244127 +300244126 +300387497 +300386437 +300404673 +300021016 +300386886 +300379994 +300400774 +300056548 +300262942 +300266421 +300256475 +300049946 +300411958 +300194572 +300194573 +300019255 +300411334 diff --git a/sensitivity_markers/selected_cases/aat_nl_case1_with_markers.txt b/sensitivity_markers/selected_cases/aat_nl_case1_with_markers.txt new file mode 100644 index 0000000..0db1833 --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_nl_case1_with_markers.txt @@ -0,0 +1,7 @@ +300386060 +300310690 +300017437 +300386794 +300056500 +300016430 +300230899 diff --git a/sensitivity_markers/selected_cases/aat_nl_case2.txt b/sensitivity_markers/selected_cases/aat_nl_case2.txt new file mode 100644 index 0000000..176fcb5 --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_nl_case2.txt @@ -0,0 +1,12 @@ +300025925 +300189309 +300197021 +300391091 +300400505 +300343888 +300390978 +300400774 +300194572 +300194573 +300411334 +300404070 diff --git a/sensitivity_markers/selected_cases/aat_nl_case2_with_markers.txt b/sensitivity_markers/selected_cases/aat_nl_case2_with_markers.txt new file mode 100644 index 0000000..c2b4bcc --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_nl_case2_with_markers.txt @@ -0,0 +1,2 @@ +300017437 +300389818 diff --git a/sensitivity_markers/selected_cases/aat_nl_case3.txt b/sensitivity_markers/selected_cases/aat_nl_case3.txt new file mode 100644 index 0000000..000348d --- /dev/null +++ b/sensitivity_markers/selected_cases/aat_nl_case3.txt @@ -0,0 +1,279 @@ +300264779 +300264782 +300264769 +300120040 +300021861 +300264761 +300120045 +300264310 +300262832 +300016575 +300021550 +300027015 +300016928 +300198715 +300387448 +300411782 +300417674 +300386795 +300262022 +300024841 +300393209 +300393207 +300224239 +300258978 +300379071 +300236519 +300236032 +300108235 +300262891 +300264436 +300263397 +300265329 +300263940 +300114633 +300016594 +300375367 +300410257 +300107052 +300343857 +300120165 +300410258 +300410260 +300386148 +300266481 +300012262 +300391253 +300374940 +300230291 +300249198 +300198715 +300020204 +300386795 +300265519 +300037086 +300264498 +300264320 +300228512 +300018959 +300264337 +300262022 +300263109 +300102489 +300388363 +300017437 +300389818 +300417373 +300400818 +300385958 +300386378 +300386397 +300386963 +300403938 +300404360 +300386193 +300263499 +300262489 +300263160 +300263069 +300263173 +300262675 +300016414 +300263105 +300025929 +300391091 +300185659 +300250642 +300343487 +300055684 +300263129 +300261803 +300343481 +300264568 +300012010 +300011611 +300263717 +300011162 +300404150 +300387445 +300262587 +300227861 +300028517 +300375370 +300232779 +300068848 +300206232 +300006777 +300163812 +300122943 +300389935 +300310238 +300015676 +300019260 +300310667 +300391483 +300393250 +300106814 +300310320 +300055475 +300265019 +300400510 +300016575 +300017635 +300017650 +300017596 +300016954 +300016773 +300017608 +300055999 +300251739 +300385956 +300107947 +300018863 +300198715 +300018279 +300262949 +300386198 +300386197 +300262632 +300386028 +300386793 +300387870 +300107847 +300380043 +300386794 +300404070 +300020502 +300312336 +300388760 +300386485 +300016282 +300264993 +300018564 +300107847 +300017437 +300387326 +300263793 +300411925 +300017447 +300375156 +300055999 +300411929 +300388363 +300265219 +300230852 +300224239 +300226631 +300265048 +300210025 +300210737 +300265171 +300265173 +300018959 +300265512 +300004376 +300264479 +300264389 +300404720 +300018436 +300386479 +300387497 +300386437 +300140253 +300011200 +300021170 +300386125 +300233431 +300386886 +300298733 +300386937 +300020944 +300198715 +300052763 +300263267 +300054588 +300264541 +300387384 +300054570 +300137801 +300054687 +300254807 +300386824 +300386686 +300174254 +300264910 +300019289 +300010630 +300056548 +300264080 +300020074 +300264837 +300106828 +300174254 +300056500 +300143666 +300016430 +300262764 +300042254 +300264475 +300265422 +300264217 +300055303 +300055304 +300017437 +300249198 +300386795 +300258488 +300055309 +300021551 +300019537 +300411927 +300233279 +300198715 +300393224 +300404865 +300018407 +300386176 +300049957 +300264813 +300019487 +300049946 +300120077 +300056460 +300111159 +300056500 +300400510 +300400504 +300018409 +300194572 +300022022 +300386075 +300194573 +300018410 +300259515 +300262022 +300113534 +300310533 +300011561 +300266176 +300266418 +300310633 +300020155 +300264810 +300375570 +300310568 +300042168 +300404069 +300411970 +300126370 +300111210 +300310524 +300310579 +300310633 +300400554 +300375682 +300310410 +300264810 +300021874 +300375570 +300393256 diff --git a/sensitivity_markers/selected_cases/count_by_cases.csv b/sensitivity_markers/selected_cases/count_by_cases.csv new file mode 100644 index 0000000..6841373 --- /dev/null +++ b/sensitivity_markers/selected_cases/count_by_cases.csv @@ -0,0 +1,7 @@ +dataset, case_1, case_1_with_markers, case_2, case_2_with_markers, case_3, case_4, case_5, case_5_with_markers +wd_en, 354, 10, 296, 10, 210, NA, NA, NA +wd_nl, 309, 12, 125, 7, 137, NA, NA, NA +aat_en, 45, 13, 128, 27, 342, NA, NA, NA +aat_nl, 48, 7, 12, 2, 279, NA, NA, NA +pwn, NA, NA, NA, NA, NA, 370, 111, 13 +odwn, NA, NA, NA, NA, NA, 303, 72, 14 \ No newline at end of file diff --git a/sensitivity_markers/selected_cases/odwn_case4.txt b/sensitivity_markers/selected_cases/odwn_case4.txt new file mode 100644 index 0000000..5b9d101 --- /dev/null +++ b/sensitivity_markers/selected_cases/odwn_case4.txt @@ -0,0 +1,303 @@ +eng-30-04923743-n +eng-30-04923743-n +eng-30-04923743-n +eng-30-04923743-n +eng-30-04923743-n +odwn-10-104552692-v +eng-30-04923743-n +odwn-10-107675980-v +eng-30-07970721-n +eng-30-10157549-n +odwn-10-106166180-v +eng-30-04923743-n +eng-30-01774799-v +eng-30-10577284-n +eng-30-07970721-n +eng-30-10157549-n +eng-30-04923743-n +eng-30-04923743-n +eng-30-04923743-n +odwn-10-101546688-n +eng-30-13980288-n +eng-30-13427078-n +eng-30-07959269-n +eng-30-01237415-n +eng-30-10553402-n +eng-30-00386390-v +eng-30-05892651-n +odwn-10-109911010-n +eng-30-02396205-v +eng-30-02396205-v +odwn-10-103725642-v +eng-30-10053808-n +eng-30-10582154-n +eng-30-00874537-v +eng-30-09928451-n +odwn-10-101393848-n +odwn-10-105858995-v +eng-30-09928451-n +eng-30-07972425-n +eng-30-04752221-n +odwn-10-103281025-v +eng-30-05238282-n +odwn-10-100513750-n +odwn-10-103063347-n +eng-30-09976551-n +r_n-41437 +odwn-10-100513750-n +eng-30-10157549-n +odwn-10-100481401-n +eng-30-01207609-n +odwn-10-104668187-n +eng-30-09178999-n +odwn-10-107188952-n +odwn-10-106126041-v +odwn-10-107188952-n +eng-30-09541125-n +eng-30-03929202-n +r_n-40975 +odwn-10-107289312-n +eng-30-05689249-n +odwn-10-104805949-n +eng-30-10352299-n +odwn-10-104805949-n +eng-30-10158756-n +eng-30-10158756-n +eng-30-10158756-n +eng-30-10158756-n +r_n-17866 +r_n-18195 +eng-30-02437707-v +eng-30-02437707-v +odwn-10-102949140-n +odwn-10-103405559-n +eng-30-05139094-n +odwn-10-104127784-n +eng-30-14881303-n +odwn-10-101073990-n +eng-30-03648219-n +r_n-42491 +odwn-10-100117009-n +odwn-10-106678037-n +eng-30-04589745-n +c_545556 +odwn-10-106133313-n +odwn-10-100117009-n +odwn-10-106133313-n +odwn-10-106678037-n +odwn-10-108706678-v +eng-30-10158756-n +eng-30-14052403-n +eng-30-14052403-n +eng-30-14052403-n +eng-30-14052403-n +eng-30-14052403-n +eng-30-14052403-n +eng-30-05689249-n +odwn-10-107547362-n +eng-30-10158756-n +odwn-10-107547362-n +eng-30-00849080-v +eng-30-10076033-n +r_n-16996 +eng-30-10076033-n +odwn-10-109472945-n +eng-30-10173895-n +eng-30-10182913-n +eng-30-10182913-n +eng-30-10182913-n +odwn-10-105972128-n +eng-30-10254965-n +eng-30-10254965-n +odwn-10-105972128-n +eng-30-00844254-n +eng-30-04623113-n +eng-30-10076033-n +eng-30-10076033-n +odwn-10-109248619-n +r_n-24975 +odwn-10-109248619-n +odwn-10-106171034-n +odwn-10-100513750-n +odwn-10-100513750-n +odwn-10-107563512-v +odwn-10-102987666-v +r_v-3090 +odwn-10-101961229-n +eng-30-02635659-v +odwn-10-104880448-v +eng-30-04458633-n +eng-30-02503803-v +odwn-10-101961229-n +eng-30-08673039-n +eng-30-10505732-n +r_n-38724 +r_n-39603 +eng-30-10505732-n +eng-30-08673039-n +odwn-10-101655623-n +eng-30-08058098-n +eng-30-07557434-n +eng-30-14917635-n +eng-30-02503517-n +eng-30-07557434-n +eng-30-12401684-n +odwn-10-101655623-n +odwn-10-104600207-n +odwn-10-104600207-n +eng-30-12268246-n +odwn-10-109739636-n +odwn-10-102422747-n +eng-30-12268246-n +odwn-10-104714918-n +r_n-24303 +eng-30-01189427-v +r_n-18442 +r_n-38586 +eng-30-10410815-n +odwn-10-109860771-n +eng-30-10506544-n +r_n-33979 +eng-30-10506544-n +odwn-10-109860771-n +eng-30-09815790-n +eng-30-02496816-v +r_n-24307 +odwn-10-107075238-n +odwn-10-107075238-n +eng-30-03788195-n +eng-30-03788195-n +odwn-10-102610292-n +eng-30-09638009-n +eng-30-09638009-n +eng-30-09638009-n +eng-30-09638009-n +odwn-10-101064198-n +odwn-10-106512680-n +r_n-35060 +eng-30-06201908-n +odwn-10-106512680-n +odwn-10-101064198-n +odwn-10-105383688-n +odwn-10-102951676-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-00721437-v +eng-30-04767347-n +eng-30-04767347-n +eng-30-09460312-n +eng-30-00076196-n +eng-30-02154508-v +r_n-40901 +eng-30-02154508-v +odwn-10-102951676-v +odwn-10-100905185-v +eng-30-08195636-n +odwn-10-107793684-n +eng-30-08195636-n +odwn-10-108219147-n +odwn-10-108533146-n +eng-30-08195636-n +eng-30-08195636-n +odwn-10-108533146-n +eng-30-01080366-n +eng-30-02932400-n +eng-30-10553402-n +eng-30-01558993-n +eng-30-10553402-n +eng-30-02932400-n +eng-30-00910203-n +eng-30-09627462-n +eng-30-09627462-n +eng-30-09183693-n +odwn-10-108984511-n +eng-30-10502950-n +odwn-10-100937974-n +eng-30-07967382-n +eng-30-14410918-n +odwn-10-104772963-n +eng-30-14410918-n +odwn-10-108984511-n +odwn-10-104772963-n +eng-30-10502950-n +eng-30-14410918-n +eng-30-14410918-n +eng-30-10157549-n +eng-30-00850425-n +eng-30-01155044-n +odwn-10-107524753-v +eng-30-10157549-n +eng-30-01155044-n +eng-30-00850425-n +eng-30-10609325-n +eng-30-09976551-n +eng-30-09976551-n +eng-30-13997253-n +eng-30-10580535-n +eng-30-13997253-n +odwn-10-109472945-n +eng-30-00623545-n +eng-30-01114284-n +eng-30-02256998-v +eng-30-00623545-n +eng-30-01114284-n +eng-30-13164763-n +eng-30-13164763-n +eng-30-06320569-n +eng-30-12731714-n +eng-30-00251791-v +eng-30-07970721-n +r_v-4063 +eng-30-07969695-n +eng-30-07970721-n +eng-30-02624263-v +eng-30-02624263-v +odwn-10-102673566-n +eng-30-01236947-n +odwn-10-102673566-n +r_n-12184 +odwn-10-108925479-n +r_v-9494 +r_n-10214 +eng-30-08366753-n +eng-30-05793554-n +r_v-2880 +odwn-10-105865991-n +eng-30-07966140-n +odwn-10-100529782-n +eng-30-13941469-n +r_n-43414 +eng-30-02133435-v +eng-30-09921409-n +odwn-10-105591402-n +odwn-10-102601580-n +eng-30-09873899-n +eng-30-14649197-n +eng-30-09762509-n +eng-30-07687053-n +r_n-44471 +odwn-10-100857451-v +eng-30-10154186-n +odwn-10-107418910-n +odwn-10-103179139-n +odwn-10-107418910-n +odwn-10-103179139-n +eng-30-01893825-n +odwn-10-105801592-n +eng-30-02133435-v +eng-30-01893825-n +odwn-10-105801592-n +odwn-10-105591402-n +odwn-10-108091031-n +odwn-10-108091031-n +eng-30-09859038-n +odwn-10-108091031-n +odwn-10-103541331-n +odwn-10-103541331-n +eng-30-10157549-n diff --git a/sensitivity_markers/selected_cases/odwn_case5.txt b/sensitivity_markers/selected_cases/odwn_case5.txt new file mode 100644 index 0000000..79650a1 --- /dev/null +++ b/sensitivity_markers/selected_cases/odwn_case5.txt @@ -0,0 +1,72 @@ +odwn-10-101180571-n +eng-30-09921409-n +eng-30-05646218-n +r_n-2619 +eng-30-06009086-n +eng-30-08510456-n +eng-30-04923743-n +eng-30-09484465-n +odwn-10-106744972-n +eng-30-10390902-n +eng-30-10053808-n +eng-30-10582154-n +odwn-10-101847342-n +r_n-6688 +eng-30-08715390-n +r_n-7429 +odwn-10-103541331-n +odwn-10-103272943-n +eng-30-06918215-n +eng-30-04799133-n +eng-30-10182913-n +eng-30-01327322-n +eng-30-10157378-n +eng-30-10157549-n +eng-30-14548343-n +odwn-10-101168606-n +eng-30-14052403-n +eng-30-05689249-n +c_546595 +eng-30-10172080-n +odwn-10-108184026-n +r_n-16996 +eng-30-00858060-n +eng-30-10182913-n +odwn-10-103586613-n +odwn-10-106518418-n +r_n-18189 +odwn-10-100569798-n +r_n-18442 +r_n-19229 +eng-30-10292192-n +eng-30-10308938-n +eng-30-02496816-v +odwn-10-101160806-n +eng-30-10163452-n +eng-30-10626439-n +odwn-10-100513750-n +odwn-10-107525787-n +odwn-10-106363474-n +eng-30-09636339-n +odwn-10-105801592-n +eng-30-09638454-n +odwn-10-106536961-n +eng-30-09636339-n +eng-30-02154508-v +eng-30-02128066-v +eng-30-00721437-v +odwn-10-108767604-v +eng-30-08167046-n +eng-30-10391086-n +r_n-27354 +odwn-10-100937974-n +eng-30-07967382-n +eng-30-10609325-n +eng-30-09976551-n +odwn-10-107447736-n +r_v-7184 +eng-30-02624263-v +r_n-38274 +r_n-38275 +eng-30-10726031-n +eng-30-09636339-n diff --git a/sensitivity_markers/selected_cases/odwn_case5_with_markers.txt b/sensitivity_markers/selected_cases/odwn_case5_with_markers.txt new file mode 100644 index 0000000..dd86658 --- /dev/null +++ b/sensitivity_markers/selected_cases/odwn_case5_with_markers.txt @@ -0,0 +1,14 @@ +eng-30-10410815-n +eng-30-09879297-n +eng-30-10040344-n +eng-30-00856847-n +odwn-10-103201483-n +eng-30-10410815-n +odwn-10-100082478-n +eng-30-10035809-n +eng-30-10040344-n +eng-30-10197525-n +eng-30-09638009-n +eng-30-09638009-n +eng-30-09638009-n +eng-30-09859038-n diff --git a/sensitivity_markers/selected_cases/pwn_case4.txt b/sensitivity_markers/selected_cases/pwn_case4.txt new file mode 100644 index 0000000..f8f2575 --- /dev/null +++ b/sensitivity_markers/selected_cases/pwn_case4.txt @@ -0,0 +1,370 @@ +aboriginal.s.02 +native.a.03 +australia.n.01 +native.n.01 +dravidian.n.01 +alaska_native.n.01 +barbarian.s.01 +attila.n.01 +odoacer.n.01 +sack.v.01 +tuareg.n.02 +almoravid.n.01 +moor.n.01 +tuareg.n.01 +riff.n.01 +berbers.n.01 +black.a.02 +bordered.a.01 +black-and-white.s.03 +black-and-white.s.03 +black-and-white.s.03 +field_cricket.n.01 +negritude.n.01 +gospel.n.03 +soul.n.05 +ku_klux_klan.n.01 +abkhaz.n.02 +gujarat.n.01 +farsi.n.01 +yellow-throated_marten.n.01 +kamarupan.n.01 +loloish.n.01 +kachin.n.01 +kuki.n.01 +naga.n.01 +irrawaddy.n.01 +stilwell.n.01 +pepper.n.01 +calcuttan.a.01 +black_hole_of_calcutta.n.01 +mumbai.n.01 +siraj-ud-daula.n.01 +originate.v.03 +caucasian.s.02 +caucasian.a.01 +chechen.n.02 +circassian.n.03 +georgian.n.03 +ubykh.n.01 +aryan.n.01 +half-breed.n.01 +metis.n.01 +colored.a.01 +colored.a.01 +light.a.02 +thimerosal.n.01 +granny's_bonnets.n.01 +moniliaceae.n.01 +earth_color.n.01 +sardonyx.n.01 +toner.n.02 +ancestral.s.01 +lineal.a.01 +unilateral.s.02 +relative.n.02 +generation.n.02 +jew.n.01 +tay-sachs_disease.n.01 +external.s.03 +international_bank_for_reconstruction_and_development.n.01 +permanently.r.01 +physical_rehabilitation.n.01 +personal_care.n.01 +disability_insurance.n.01 +sheltered_workshop.n.01 +living_will.n.01 +disabled.n.01 +disability_check.n.01 +disable.v.02 +ascertain.v.04 +discover.v.04 +trace.v.01 +detect.v.01 +locate.v.01 +dwarfish.s.01 +dwarfish.s.01 +microcephalic.a.01 +troll.n.01 +pituitary_dwarf.n.01 +primordial_dwarf.n.01 +dryadella.n.01 +one-flowered_wintergreen.n.01 +wild_thyme.n.01 +tupik.n.01 +eskimo-aleut.n.01 +eskimo.n.02 +aleut.n.02 +aleut.n.02 +lake_clark_national_park.n.01 +eskimo.n.01 +syllabic.a.02 +kayak.n.01 +rasmussen.n.01 +ethnocentric.a.01 +pogrom.n.01 +communalism.n.02 +ethnocentrism.n.01 +peoples.n.01 +ghetto.n.03 +pathan.n.01 +kurd.n.01 +multiethnic.s.01 +desegregate.v.01 +ethnically.r.01 +ethnicity.n.01 +exotic.s.02 +exotic.s.02 +exotic.s.02 +alien.s.02 +alien.s.02 +ecotourism.n.01 +pasty.n.02 +exoticism.n.01 +biosafety_level_4.n.01 +erupt.v.07 +romance.v.04 +introduce.v.05 +armageddon.n.02 +commemorate.v.02 +lackey.n.01 +liveried.a.01 +bright.s.09 +gay.s.03 +gay.s.03 +gaily.r.01 +antonym.n.01 +gaiety.n.01 +ghetto.n.02 +out.v.02 +excommunicate.v.01 +romany.a.01 +flamenco.n.02 +romany.n.02 +exterminate.v.01 +roll.v.12 +chiromance.v.01 +gypsy.n.03 +tinker.n.02 +penalty.n.04 +welterweight.n.01 +succeed.v.01 +albatross.n.01 +pseudohermaphrodite.n.01 +sapiens.a.01 +pithecanthropus.n.01 +javanthropus.n.01 +language.n.05 +homophobic.s.01 +gay.s.06 +lesbian.s.01 +tribadistic.a.01 +heterosexism.n.01 +beard.n.03 +closet_queen.n.01 +butch.s.02 +old_country.n.01 +ethiopian.a.01 +nationality.n.01 +immigration.n.02 +coyote.n.02 +assimilate.v.03 +immigrate.v.02 +settle.v.04 +restrain.v.01 +indian.a.02 +indian.a.01 +indian.a.01 +brahman.n.04 +athapaskan.n.01 +mayan.n.01 +chinook.n.02 +shoshone.n.01 +half-breed.n.01 +jat.n.01 +wickiup.n.01 +autochthonal.s.01 +substrate.n.04 +superstrate.n.02 +chukchi.n.02 +ural-altaic.n.01 +finno-ugric.n.01 +peoples.n.01 +lapp.n.01 +native_hawaiian.n.01 +chukchi.n.01 +indo-european.a.01 +armenian.n.02 +thraco-phrygian.n.01 +balto-slavic.n.01 +baltic.n.02 +germanic.n.01 +english.n.01 +tocharian.n.01 +anatolian.n.01 +jat.n.01 +nunavut.n.01 +nunavut.n.01 +eskimo.n.01 +fiddling.s.01 +bantam.s.01 +lilliputian.a.01 +lilliputian.n.01 +savara.n.02 +chennai.n.01 +tamil_nadu.n.01 +ketembilla.n.02 +maroon.n.01 +leopard_lily.n.01 +snake's_head_fritillary.n.01 +hog_peanut.n.01 +hyacinth_bean.n.01 +rainmaker.n.02 +criollo.n.01 +mongoloid.a.01 +mongoloid.n.01 +marston_moor.n.01 +converso.n.01 +moorish.a.01 +alcazar.n.01 +granada.n.01 +ferdinand.n.01 +cornish_heath.n.01 +broom_tree.n.01 +quadroon.n.01 +native.a.01 +native.a.01 +native.a.03 +endemic.a.02 +emigration.n.01 +asian_tiger_mosquito.n.01 +aleut.n.02 +brinton.n.01 +whitman.n.02 +fox_grape.n.01 +native.n.01 +blackface.n.01 +minstrel_show.n.01 +liberia.n.01 +black.n.05 +white.s.05 +western.a.01 +oriental.s.01 +incidentally.r.02 +martial_art.n.01 +selvage.n.01 +fluidity.n.02 +neoplatonism.n.01 +orientalist.n.01 +tobey.n.01 +armillaria_ponderosa.n.01 +social.a.03 +example.n.01 +playbook.n.03 +opinion.n.02 +disorganized.a.01 +absurd.s.02 +family_bible.n.01 +belong_to.v.01 +appellative.s.02 +crude.s.04 +crude.s.04 +primitive.s.04 +generalized.s.01 +primitively.r.02 +monera.n.01 +trickster.n.03 +hamamelidae.n.01 +massasauga.n.02 +ground_rattler.n.01 +gowen_cypress.n.01 +cosmopolitan.a.02 +curious.s.01 +fishy.s.02 +rigout.n.01 +equal_opportunity.n.01 +supremacism.n.01 +linguistic_profiling.n.01 +discussion.n.01 +racial_immunity.n.01 +racial.a.02 +miscegenation.n.01 +ethnology.n.01 +race.n.03 +negative.s.03 +retarded.a.01 +backward.s.03 +developmentally.r.01 +mentally_retarded.n.01 +mentally_retarded.n.01 +idiot_savant.n.01 +still's_disease.n.01 +pink.v.02 +research.v.02 +domestic.a.02 +domestic.n.01 +housekeeper.n.01 +skivvy.n.01 +serve.v.10 +trustworthy.s.02 +merit_system.n.01 +spoils_system.n.01 +retain.v.02 +slave.n.03 +slave.n.03 +slave.n.03 +clay.n.04 +enslavement.n.01 +servile.s.02 +antagonistic.s.02 +slavery.n.02 +action.n.09 +manumission.n.01 +ku_klux_klan.n.01 +convert.v.02 +teeming.s.01 +traditional.a.01 +traditional.a.01 +traditional.s.02 +mongoloid.a.02 +kabbalism.n.02 +traditionalism.n.01 +confucianism.n.01 +neoconservatism.n.01 +basque_homeland_and_freedom.n.01 +beat_generation.n.01 +tory.n.03 +elaidic_acid.n.01 +zapotec.n.01 +menomini.n.01 +inmarry.v.01 +shamanism.n.01 +nation.n.04 +amphictyony.n.01 +chinook.n.02 +indian_agent.n.01 +tribalism.n.01 +western.a.01 +western.a.01 +western.a.01 +occidental.s.01 +malay.a.01 +west_african.n.01 +dichotomy.n.01 +world.n.02 +bengal.n.01 +haiti.n.01 +darfur.n.01 +athapaskan.n.01 +white.a.02 +black-and-white.s.03 +black-and-white.s.03 +black-and-white.s.03 +prejudicial.a.02 +miscegenation.n.01 +prerogative.n.01 +supremacism.n.01 +white_separatism.n.01 +white.s.05 +color_barrier.n.01 +color_bar.n.01 diff --git a/sensitivity_markers/selected_cases/pwn_case5.txt b/sensitivity_markers/selected_cases/pwn_case5.txt new file mode 100644 index 0000000..3db09ee --- /dev/null +++ b/sensitivity_markers/selected_cases/pwn_case5.txt @@ -0,0 +1,111 @@ +native.n.01 +native.a.03 +aboriginal.s.02 +savage.n.01 +peasant.n.03 +barbarian.s.01 +berber.n.01 +berber.n.02 +berbers.n.01 +black.a.02 +mumbai.n.01 +myanmar.n.01 +kolkata.n.01 +caucasian.n.02 +caucasian.a.01 +caucasian.s.02 +colored.a.01 +colored.s.02 +bleached.s.02 +origin.n.02 +descent.n.04 +lineage.n.01 +disabled.n.01 +disabled.s.01 +detect.v.01 +learn.v.02 +discover.v.03 +discover.v.04 +fall_upon.v.01 +unwrap.v.02 +discover.v.07 +dwarf.n.01 +dwarf.n.03 +eskimo.n.02 +ethnicity.n.01 +alien.s.02 +exotic.s.02 +footman.n.01 +homosexual.n.01 +gay.s.03 +gay.s.06 +itinerant.n.01 +gypsy.n.02 +gypsy.n.03 +half-blooded.s.01 +disability.n.01 +handicap.n.02 +hindrance.n.01 +disable.v.02 +handicap.v.02 +handicap.v.03 +headhunter.n.02 +hermaphrodite.n.01 +hermaphroditic.s.02 +homosexual.n.01 +homo.n.02 +homosexual.n.01 +homosexual.a.01 +khoikhoin.n.01 +immigrant.n.01 +indian.a.01 +indian.a.02 +autochthonal.s.01 +great_millet.n.01 +lilliputian.n.01 +lilliputian.a.01 +bantam.s.01 +maroon.n.01 +maroon.n.03 +maroon.v.01 +maroon.v.02 +mestizo.n.01 +metis.n.01 +mohammedan.n.01 +muhammadan.a.01 +mongoloid.n.01 +mongoloid.a.01 +mongoloid.a.02 +moor.n.01 +moor.n.02 +mulatto.n.01 +native.a.01 +native.a.03 +colored.s.02 +oriental.s.01 +page.n.05 +page.n.06 +primitive.n.01 +primitive.n.02 +crude.s.04 +primitive.s.04 +crudeness.n.01 +primitivism.n.02 +pygmy.n.01 +pygmy.n.02 +thwart.v.01 +queer.v.02 +curious.s.01 +gay.s.06 +subspecies.n.01 +mentally_retarded.n.01 +retarded.a.01 +servant.n.01 +slave.n.03 +traditional.a.01 +traditional.s.02 +transvestite.n.01 +transvestic.a.01 +tribe.n.01 +western.a.01 +white.a.02 diff --git a/sensitivity_markers/selected_cases/pwn_case5_with_markers.txt b/sensitivity_markers/selected_cases/pwn_case5_with_markers.txt new file mode 100644 index 0000000..fb6c687 --- /dev/null +++ b/sensitivity_markers/selected_cases/pwn_case5_with_markers.txt @@ -0,0 +1,13 @@ +black.n.05 +coolie.n.01 +eskimo.n.01 +half-breed.n.01 +eskimo.n.01 +kaffir.n.02 +fiddling.s.01 +tamil_nadu.n.01 +chennai.n.01 +mongoloid.n.02 +mongoloid.a.03 +black.n.05 +fagot.n.01 diff --git a/sensitivity_markers/selected_cases/wd_en_case1.txt b/sensitivity_markers/selected_cases/wd_en_case1.txt new file mode 100644 index 0000000..3a46d7a --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_en_case1.txt @@ -0,0 +1,354 @@ +Q8039318 +Q85739476 +Q2008347 +Q5402094 +Q25230522 +Q96464545 +Q96464582 +Q1199713 +Q17340464 +Q25388662 +Q48728178 +Q1150578 +Q28163844 +Q19835346 +Q2511788 +Q25448 +Q25031017 +Q16148121 +Q16209031 +Q45315 +Q105069642 +Q2903671 +Q3075017 +Q2415143 +Q96649416 +Q38007013 +Q29097370 +Q2395774 +Q32135712 +Q4940528 +Q54888757 +Q59546705 +Q13072974 +Q1937196 +Q35730552 +Q1145306 +Q17802195 +Q5018914 +Q5018950 +Q107519129 +Q112854793 +Q13277809 +Q18344570 +Q112853179 +Q5149038 +Q110626609 +Q4774147 +Q49713369 +Q50902692 +Q50902731 +Q548135 +Q99950019 +Q99621558 +Q1075815 +Q110719661 +Q333018 +Q89659343 +Q3277425 +Q5988338 +Q5263736 +Q112877807 +Q114408620 +Q24265886 +Q59638044 +Q64259423 +Q66171650 +Q67620028 +Q69948768 +Q108735754 +Q5417486 +Q73079646 +Q73187870 +Q73236563 +Q110142389 +Q5635659 +Q70954178 +Q72760884 +Q73231697 +Q1623331 +Q29370670 +Q3870126 +Q34854923 +Q112683418 +Q51440055 +Q51450655 +Q51473727 +Q51521215 +Q5398155 +Q66330780 +Q2531956 +Q41710 +Q8085998 +Q97455294 +Q107575245 +Q59581366 +Q103920449 +Q1068126 +Q112856680 +Q112903729 +Q15218857 +Q16872679 +Q104915635 +Q112158693 +Q112890352 +Q5362123 +Q876830 +Q100097293 +Q99660483 +Q107794240 +Q107865522 +Q110684852 +Q19912727 +Q4382663 +Q49638341 +Q52270723 +Q60481736 +Q17015701 +Q592 +Q849216 +Q116033699 +Q110922133 +Q19880131 +Q51412682 +Q104867069 +Q51506962 +Q51521182 +Q59935951 +Q59935954 +Q64400362 +Q64400587 +Q64402298 +Q66151028 +Q66196096 +Q66205641 +Q6990906 +Q57622943 +Q99892850 +Q112889444 +Q61965765 +Q104637757 +Q22293384 +Q22294366 +Q22294367 +Q22294368 +Q303479 +Q78644404 +Q97501247 +Q62090705 +Q116185205 +Q18349935 +Q30913057 +Q49931984 +Q79996196 +Q79996200 +Q105192793 +Q31531084 +Q5912539 +Q950463 +Q12547146 +Q2368859 +Q99743302 +Q19867974 +Q888099 +Q907924 +Q103817 +Q1493806 +Q170355 +Q2986880 +Q3557982 +Q5533462 +Q2453813 +Q3236316 +Q1661685 +Q6025564 +Q25705896 +Q2714194 +Q6059247 +Q642019 +Q7198347 +Q60788910 +Q60788914 +Q28181146 +Q64593875 +Q10853395 +Q49478269 +Q63246173 +Q65956219 +Q65959672 +Q65996060 +Q14632167 +Q17379998 +Q8756345 +Q112950919 +Q445485 +Q6127426 +Q6127428 +Q109499757 +Q111642613 +Q20486967 +Q266750 +Q49943748 +Q54641544 +Q67625494 +Q107342119 +Q15309715 +Q15355263 +Q5448617 +Q16151565 +Q6011525 +Q60188605 +Q110068902 +Q104968492 +Q113473641 +Q1471031 +Q19094101 +Q42193074 +Q60755390 +Q99222909 +Q113493444 +Q63314480 +Q11500981 +Q116457612 +Q19891911 +Q207912 +Q6899769 +Q8546951 +Q1050631 +Q2000538 +Q65075114 +Q5602882 +Q64811664 +Q15262572 +Q102276979 +Q169260 +Q115997244 +Q15259470 +Q5193390 +Q64277831 +Q97487645 +Q97495711 +Q16201620 +Q8247324 +Q8340290 +Q16910544 +Q51374013 +Q51489550 +Q42194475 +Q111047765 +Q19884575 +Q23022954 +Q98119441 +Q13860 +Q13868 +Q55074680 +Q2843868 +Q7102362 +Q7124279 +Q57946494 +Q103165303 +Q67519403 +Q63677482 +Q59168588 +Q1737209 +Q1942010 +Q6453739 +Q77177747 +Q1848870 +Q42193895 +Q51221142 +Q110142648 +Q110893128 +Q112882891 +Q114569728 +Q16591771 +Q1662181 +Q58429779 +Q59575773 +Q667672 +Q848365 +Q110142534 +Q111965527 +Q113472233 +Q13560329 +Q171927 +Q1747200 +Q24718207 +Q112950551 +Q2353191 +Q5504229 +Q2042898 +Q51430324 +Q112108108 +Q112845941 +Q112847043 +Q112847738 +Q74277620 +Q233472 +Q67521352 +Q59937323 +Q64196363 +Q64275676 +Q64278051 +Q64478652 +Q66198090 +Q11993231 +Q2313151 +Q112925771 +Q6785120 +Q106973020 +Q108291575 +Q2445443 +Q5507284 +Q100164094 +Q106811663 +Q110266495 +Q55633618 +Q750583 +Q7570403 +Q99922567 +Q99923195 +Q99923196 +Q99947952 +Q112853310 +Q112857445 +Q180194 +Q30256340 +Q59672380 +Q6052693 +Q66321661 +Q1428168 +Q4461766 +Q111949566 +Q50922905 +Q96213190 +Q1052281 +Q2449503 +Q96154453 +Q112902347 +Q7622973 +Q85810514 +Q59580078 +Q12885585 +Q133311 +Q4669719 +Q11555014 +Q15079932 +Q160381 +Q65362 +Q106993358 +Q856284 +Q278929 +Q2560112 +Q110441926 +Q8125662 diff --git a/sensitivity_markers/selected_cases/wd_en_case1_with_markers.txt b/sensitivity_markers/selected_cases/wd_en_case1_with_markers.txt new file mode 100644 index 0000000..09601d5 --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_en_case1_with_markers.txt @@ -0,0 +1,10 @@ +Q134313 +Q112078715 +Q17144151 +Q1631241 +Q2367463 +Q11410826 +Q191923 +Q7832650 +Q855855 +Q51415 diff --git a/sensitivity_markers/selected_cases/wd_en_case2.txt b/sensitivity_markers/selected_cases/wd_en_case2.txt new file mode 100644 index 0000000..bb7cc0b --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_en_case2.txt @@ -0,0 +1,296 @@ +Q103817 +Q112729549 +Q28942344 +Q5937166 +Q96200400 +Q170355 +Q3030751 +Q64140395 +Q660643 +Q15944418 +Q15944418 +Q5366110 +Q19835346 +Q2511788 +Q25448 +Q25448 +Q3071332 +Q3007177 +Q105069642 +Q105069642 +Q105069642 +Q2415143 +Q2415143 +Q1156 +Q2395774 +Q2395774 +Q3621720 +Q61445 +Q646414 +Q13072974 +Q13072974 +Q1365392 +Q2749165 +Q2749165 +Q2749165 +Q2749165 +Q2749165 +Q2749165 +Q3088844 +Q3088844 +Q3088844 +Q3088844 +Q3088844 +Q3088844 +Q4694017 +Q836 +Q836 +Q1145306 +Q1348 +Q3349812 +Q3350560 +Q18379789 +Q3198467 +Q112794323 +Q5018914 +Q5018914 +Q3286626 +Q41259 +Q6949234 +Q104341641 +Q104341641 +Q819264 +Q819264 +Q4774147 +Q2905804 +Q15978181 +Q15978181 +Q15978181 +Q16649002 +Q16649002 +Q16649002 +Q16649002 +Q69948768 +Q884271 +Q20860129 +Q29370670 +Q3870126 +Q24944599 +Q5398155 +Q2509271 +Q112903729 +Q112890352 +Q5362123 +Q17015701 +Q592 +Q592 +Q850698 +Q116033699 +Q116033699 +Q116033699 +Q116033699 +Q116033699 +Q17150753 +Q875651 +Q19880131 +Q19880131 +Q4451351 +Q12131 +Q12131 +Q16649002 +Q16649002 +Q16649002 +Q7669399 +Q290088 +Q104717073 +Q65035047 +Q1067692 +Q109291096 +Q1940866 +Q113286753 +Q592 +Q219252 +Q5912539 +Q1351807 +Q1351807 +Q2368859 +Q706601 +Q856681 +Q1932461 +Q16910544 +Q109214210 +Q322951 +Q322951 +Q322951 +Q322951 +Q322951 +Q392316 +Q478805 +Q49297 +Q49297 +Q49297 +Q49297 +Q852431 +Q907924 +Q103817 +Q103817 +Q108808000 +Q108808000 +Q1493806 +Q1493806 +Q2986880 +Q3557982 +Q907924 +Q2453813 +Q2453813 +Q2453813 +Q3236316 +Q6025564 +Q189975 +Q2905047 +Q3607819 +Q582594 +Q2419953 +Q649340 +Q1352 +Q257382 +Q286536 +Q286536 +Q502670 +Q502670 +Q65996060 +Q1903204 +Q6127426 +Q6127426 +Q17516119 +Q106713 +Q262457 +Q4763645 +Q6950150 +Q6950152 +Q1471031 +Q1135825 +Q116457612 +Q97487645 +Q16910544 +Q16910544 +Q1839674 +Q96200400 +Q109607777 +Q2638531 +Q42194475 +Q110591878 +Q111814212 +Q111814212 +Q98119441 +Q111812959 +Q111812959 +Q115826990 +Q115826990 +Q111814144 +Q111814144 +Q889394 +Q889394 +Q2030514 +Q307043 +Q307043 +Q1770351 +Q105374668 +Q105374668 +Q105374668 +Q2843868 +Q2843868 +Q1848870 +Q16591771 +Q17884 +Q17884 +Q17884 +Q22205399 +Q339014 +Q2353191 +Q2353191 +Q235155 +Q2042898 +Q2042898 +Q2042898 +Q2042898 +Q2042898 +Q2042898 +Q2042898 +Q22273995 +Q3254959 +Q3254959 +Q111469956 +Q19709948 +Q55602941 +Q42899432 +Q42899432 +Q2313151 +Q54128 +Q54128 +Q54128 +Q599151 +Q6785120 +Q464705 +Q1890568 +Q841571 +Q841571 +Q841571 +Q106611758 +Q106811663 +Q337352 +Q4461766 +Q96200400 +Q105222132 +Q1052281 +Q1052281 +Q1052281 +Q1052281 +Q1052281 +Q1771029 +Q1771029 +Q189125 +Q189125 +Q189125 +Q189125 +Q189125 +Q2449503 +Q2449503 +Q2449503 +Q2449503 +Q2449503 +Q27679684 +Q27679684 +Q27679684 +Q27679684 +Q27679766 +Q27679766 +Q27679766 +Q27679766 +Q27679766 +Q96154453 +Q85810459 +Q110651958 +Q102090 +Q12885585 +Q12885585 +Q12885585 +Q133311 +Q15270596 +Q15270596 +Q15270596 +Q15270596 +Q15270596 +Q15270596 +Q15270596 +Q15270596 +Q1500686 +Q1500686 +Q160381 +Q160381 +Q160381 +Q1253290 +Q3328669 +Q278929 +Q278929 +Q235155 diff --git a/sensitivity_markers/selected_cases/wd_en_case2_with_markers.txt b/sensitivity_markers/selected_cases/wd_en_case2_with_markers.txt new file mode 100644 index 0000000..d1a2ac1 --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_en_case2_with_markers.txt @@ -0,0 +1,10 @@ +Q817393 +Q5207989 +Q1285250 +Q855855 +Q115870510 +Q115870510 +Q12773225 +Q1617492 +Q7129609 +Q7129609 diff --git a/sensitivity_markers/selected_cases/wd_en_case3.txt b/sensitivity_markers/selected_cases/wd_en_case3.txt new file mode 100644 index 0000000..5cc2741 --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_en_case3.txt @@ -0,0 +1,210 @@ +Q596718 +Q96200400 +Q8039318 +Q7980672 +Q5366110 +Q110939710 +Q116046852 +Q23043356 +Q48728178 +Q96242430 +Q1150578 +Q28163844 +Q1267932 +Q1541828 +Q19835346 +Q2511788 +Q3071332 +Q410453 +Q2415143 +Q38007013 +Q29097370 +Q7525357 +Q1937196 +Q524272 +Q1651832 +Q1152826 +Q3832962 +Q105825358 +Q1786363 +Q22282519 +Q22296285 +Q312266 +Q353267 +Q50429925 +Q2996542 +Q107804051 +Q183905 +Q89659343 +Q1321675 +Q2905804 +Q5263736 +Q1073779 +Q7012550 +Q7692521 +Q67374899 +Q104763821 +Q67527673 +Q28744885 +Q64869775 +Q193275 +Q29370670 +Q1920404 +Q63441638 +Q2384573 +Q1246654 +Q5398155 +Q603749 +Q641154 +Q666758 +Q212926 +Q2462146 +Q2531956 +Q2640974 +Q5404271 +Q110441926 +Q97455294 +Q112873503 +Q6266 +Q7604529 +Q80100972 +Q89668650 +Q89669411 +Q113465752 +Q1401536 +Q15218857 +Q1920232 +Q3723095 +Q61989753 +Q211168 +Q5362123 +Q85816262 +Q60463389 +Q897404 +Q63883739 +Q51424 +Q40246 +Q110266417 +Q5207989 +Q979368 +Q116033699 +Q105395491 +Q113095566 +Q5508820 +Q64847362 +Q6902629 +Q6484187 +Q22293384 +Q22294371 +Q22302199 +Q22302200 +Q5 +Q95724150 +Q45316543 +Q1797885 +Q50299201 +Q211354 +Q2256824 +Q24707892 +Q849216 +Q12276157 +Q2368859 +Q4745593 +Q5251504 +Q90957522 +Q108808000 +Q2986880 +Q3339252 +Q3573248 +Q192170 +Q3236316 +Q792316 +Q149386 +Q1815070 +Q6025564 +Q4342542 +Q3832962 +Q1671647 +Q17036301 +Q25705896 +Q2714194 +Q603749 +Q641942 +Q6345995 +Q65956219 +Q1542741 +Q1415423 +Q104853010 +Q6144422 +Q3088076 +Q4974225 +Q11410826 +Q29496769 +Q98596477 +Q31501365 +Q104846812 +Q13315 +Q7856433 +Q1839674 +Q109938005 +Q1305793 +Q2638531 +Q110426727 +Q55074680 +Q1451816 +Q30834875 +Q19662080 +Q134313 +Q1382550 +Q1942010 +Q3760350 +Q51221142 +Q113471961 +Q24718207 +Q3039820 +Q5624044 +Q110266417 +Q104833913 +Q2353191 +Q30103 +Q64711016 +Q57203016 +Q365143 +Q1141593 +Q115542878 +Q7921702 +Q42899432 +Q44602668 +Q673079 +Q740628 +Q1617492 +Q2928426 +Q12011559 +Q6281693 +Q7692521 +Q108443879 +Q111934605 +Q86669572 +Q111949566 +Q7980672 +Q106246204 +Q107498865 +Q111145560 +Q115571526 +Q115605951 +Q322335 +Q581839 +Q4669719 +Q56685910 +Q484206 +Q1820260 +Q6034912 +Q106993358 +Q2640158 +Q2072081 +Q278929 +Q106677040 +Q2560112 +Q110441926 +Q64711016 +Q3511034 diff --git a/sensitivity_markers/selected_cases/wd_nl_case1.txt b/sensitivity_markers/selected_cases/wd_nl_case1.txt new file mode 100644 index 0000000..15becd8 --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_nl_case1.txt @@ -0,0 +1,309 @@ +Q2479183 +Q100341850 +Q5375657 +Q110629929 +Q10388983 +Q55350216 +Q9031543 +Q2098138 +Q55829603 +Q111256319 +Q1979583 +Q2008347 +Q28090055 +Q43088035 +Q189169 +Q2469867 +Q2498891 +Q57506011 +Q57513626 +Q106686922 +Q1199713 +Q2436746 +Q4868680 +Q84322891 +Q2117912 +Q45021418 +Q57076065 +Q71171864 +Q21143451 +Q2152757 +Q375935 +Q3807949 +Q818743 +Q100340157 +Q2712462 +Q33061123 +Q45315 +Q55355256 +Q2376315 +Q2563642 +Q2664805 +Q2664807 +Q2666064 +Q2666080 +Q2667140 +Q704358 +Q776524 +Q2560112 +Q49078 +Q59786221 +Q22909760 +Q235155 +Q2550212 +Q1348 +Q5018950 +Q100340135 +Q100341393 +Q180194 +Q20656136 +Q85318651 +Q10477881 +Q136562 +Q17480821 +Q56299838 +Q5871 +Q5976 +Q3478903 +Q56508630 +Q876830 +Q100342131 +Q19365020 +Q20736 +Q51512437 +Q8421920 +Q131242 +Q2659059 +Q3347113 +Q5404323 +Q7128854 +Q41710 +Q4204501 +Q105999586 +Q1496534 +Q592 +Q1383254 +Q111748392 +Q3723183 +Q55186653 +Q15978181 +Q18089065 +Q2380034 +Q2523708 +Q29584864 +Q47189385 +Q61857538 +Q1836236 +Q2072081 +Q22245963 +Q4854529 +Q61944902 +Q8230758 +Q18336298 +Q1179623 +Q12131 +Q1818174 +Q29584860 +Q29584861 +Q42255152 +Q22257088 +Q28097260 +Q303479 +Q105784 +Q3786468 +Q40221 +Q1348938 +Q1626313 +Q18349938 +Q27333507 +Q3882309 +Q6457893 +Q6636 +Q8035007 +Q8225766 +Q113286753 +Q104969456 +Q17015701 +Q2249431 +Q100340285 +Q100341399 +Q16910544 +Q47534052 +Q6979964 +Q605901 +Q652560 +Q1270312 +Q100341198 +Q826616 +Q215643 +Q240123 +Q475027 +Q269145 +Q60741209 +Q61896194 +Q103817 +Q1363781 +Q1493806 +Q216839 +Q3987120 +Q1945590 +Q100341039 +Q112845940 +Q100341703 +Q1091412 +Q1128374 +Q22444905 +Q887850 +Q47465549 +Q173712 +Q2294900 +Q2369794 +Q3133637 +Q3156859 +Q54898510 +Q58150158 +Q70320605 +Q9073603 +Q169921 +Q2528872 +Q38576 +Q55354560 +Q5602078 +Q108839781 +Q113974055 +Q114719888 +Q1237356 +Q17275857 +Q2487928 +Q57507224 +Q57509271 +Q548135 +Q104680922 +Q2639564 +Q6728464 +Q108960293 +Q6773021 +Q13747796 +Q14632167 +Q1903204 +Q3346785 +Q445485 +Q110368077 +Q110368731 +Q13430620 +Q266750 +Q28106968 +Q110055515 +Q190565 +Q22699415 +Q62033842 +Q89197458 +Q89903220 +Q114708177 +Q1740683 +Q26235 +Q41975 +Q469930 +Q689831 +Q842323 +Q207912 +Q6399808 +Q9246 +Q5188069 +Q889885 +Q5643661 +Q6908024 +Q28406634 +Q4849340 +Q55594749 +Q7855578 +Q169260 +Q262457 +Q21280574 +Q2196236 +Q28060300 +Q55056867 +Q57507811 +Q61857058 +Q57510667 +Q28061580 +Q29846151 +Q22990325 +Q23419078 +Q22988142 +Q23663987 +Q2180237 +Q965204 +Q27033121 +Q3309962 +Q35200609 +Q278039 +Q110734758 +Q2242450 +Q100341316 +Q17307164 +Q2864736 +Q83781188 +Q848365 +Q100341834 +Q171927 +Q98121325 +Q100938988 +Q110854357 +Q1563086 +Q58459677 +Q9031850 +Q92867534 +Q98929208 +Q104775895 +Q3254959 +Q8448318 +Q4829793 +Q4903978 +Q7489756 +Q22893595 +Q199898 +Q211052 +Q2378782 +Q133311 +Q4295650 +Q604819 +Q2395922 +Q15873930 +Q2168394 +Q3266746 +Q3289959 +Q3008357 +Q3266598 +Q1436339 +Q3133248 +Q233472 +Q2358362 +Q9337845 +Q100341852 +Q11416778 +Q15925549 +Q160381 +Q478958 +Q17142367 +Q6933946 +Q6317517 +Q20931979 +Q2436251 +Q6674339 +Q100340717 +Q50308628 +Q5455956 +Q61863123 +Q64446226 +Q145425 +Q2448416 +Q2583467 +Q41978630 +Q750583 +Q8497313 +Q1922956 +Q28648434 +Q49836450 +Q83472612 +Q817393 diff --git a/sensitivity_markers/selected_cases/wd_nl_case1_with_markers.txt b/sensitivity_markers/selected_cases/wd_nl_case1_with_markers.txt new file mode 100644 index 0000000..9b4bbee --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_nl_case1_with_markers.txt @@ -0,0 +1,12 @@ +Q107405878 +Q698752 +Q2419953 +Q189975 +Q1192767 +Q1285250 +Q855855 +Q51415 +Q7129609 +Q989255 +Q12773225 +Q76475 diff --git a/sensitivity_markers/selected_cases/wd_nl_case2.txt b/sensitivity_markers/selected_cases/wd_nl_case2.txt new file mode 100644 index 0000000..b95bcbb --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_nl_case2.txt @@ -0,0 +1,125 @@ +Q170355 +Q216839 +Q1642895 +Q423803 +Q45315 +Q905761 +Q492145 +Q936969 +Q110409649 +Q1199713 +Q84322891 +Q84322891 +Q833860 +Q21143451 +Q836 +Q1156 +Q61445 +Q61445 +Q445485 +Q445485 +Q194101 +Q41710 +Q851126 +Q104969456 +Q1496534 +Q189758 +Q958953 +Q12012782 +Q15978181 +Q183560 +Q90665701 +Q2423714 +Q183560 +Q183560 +Q16674976 +Q104969456 +Q5 +Q849216 +Q131464 +Q40221 +Q592 +Q110271724 +Q219252 +Q36747 +Q1261048 +Q6034885 +Q188161 +Q215643 +Q215643 +Q53034861 +Q215643 +Q215643 +Q215643 +Q475027 +Q475027 +Q475027 +Q2116909 +Q103817 +Q103817 +Q15571255 +Q36747 +Q36747 +Q1945590 +Q1128374 +Q888553 +Q47740 +Q161652 +Q2432369 +Q169921 +Q2088141 +Q2088141 +Q330756 +Q330756 +Q330756 +Q330756 +Q108839849 +Q108839849 +Q5060555 +Q1352 +Q16735433 +Q1709371 +Q42042 +Q106713 +Q47740 +Q689831 +Q1055705 +Q1055705 +Q110068902 +Q18574018 +Q17276026 +Q16765325 +Q177323 +Q47486214 +Q786613 +Q9053105 +Q16163906 +Q1891649 +Q11919228 +Q35200609 +Q1937269 +Q1937269 +Q667672 +Q3254959 +Q199898 +Q1104182 +Q2381172 +Q250584 +Q156108 +Q486680 +Q2358362 +Q163800 +Q17142367 +Q235155 +Q55677536 +Q113457800 +Q110158779 +Q106133380 +Q117571 +Q117571 +Q371762 +Q18434892 +Q18434892 +Q1922956 +Q107094905 +Q734967 diff --git a/sensitivity_markers/selected_cases/wd_nl_case2_with_markers.txt b/sensitivity_markers/selected_cases/wd_nl_case2_with_markers.txt new file mode 100644 index 0000000..f09ff1d --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_nl_case2_with_markers.txt @@ -0,0 +1,7 @@ +Q134313 +Q7129609 +Q2419953 +Q191923 +Q1130557 +Q7129609 +Q12773225 diff --git a/sensitivity_markers/selected_cases/wd_nl_case3.txt b/sensitivity_markers/selected_cases/wd_nl_case3.txt new file mode 100644 index 0000000..999f061 --- /dev/null +++ b/sensitivity_markers/selected_cases/wd_nl_case3.txt @@ -0,0 +1,137 @@ +Q254387 +Q1476490 +Q111248029 +Q1492906 +Q110903593 +Q12332701 +Q3023540 +Q60741209 +Q2558220 +Q4868680 +Q66737952 +Q98550142 +Q106075658 +Q106246935 +Q106686255 +Q106737573 +Q106767195 +Q99228228 +Q2072081 +Q107405878 +Q111545624 +Q50878538 +Q12413015 +Q1934607 +Q3632559 +Q4856518 +Q5003979 +Q7685715 +Q5100150 +Q67906158 +Q67911834 +Q77425397 +Q5328741 +Q67652597 +Q68159535 +Q68647181 +Q7567630 +Q4532729 +Q189975 +Q110891832 +Q111654081 +Q115771874 +Q133032 +Q7325 +Q8461 +Q851126 +Q12223 +Q154278 +Q16513600 +Q1988847 +Q3502570 +Q3676128 +Q533226 +Q506 +Q133067 +Q6544309 +Q739550 +Q114572905 +Q13635220 +Q264231 +Q105784 +Q54882501 +Q131464 +Q54882504 +Q54993583 +Q1054678 +Q27333507 +Q2335529 +Q6649 +Q16154286 +Q3323096 +Q510048 +Q109712735 +Q100341062 +Q1610219 +Q40477 +Q8752 +Q269145 +Q16908608 +Q1755300 +Q804127 +Q4532729 +Q62498853 +Q71859469 +Q2096913 +Q2655106 +Q108839781 +Q3133187 +Q3530475 +Q3534941 +Q3537400 +Q4738370 +Q5148870 +Q4746424 +Q6932073 +Q110347727 +Q26822103 +Q77046403 +Q2636673 +Q5515604 +Q1646902 +Q4966238 +Q352378 +Q75042240 +Q7937037 +Q865909 +Q944818 +Q556018 +Q1350206 +Q5202866 +Q93883800 +Q26936735 +Q100474769 +Q1571949 +Q59816 +Q1120876 +Q1830234 +Q2159754 +Q1155622 +Q601444 +Q250584 +Q4955096 +Q5373604 +Q11913408 +Q94581668 +Q7835451 +Q1365619 +Q1637806 +Q1755300 +Q42865 +Q1425676 +Q18729864 +Q6380582 +Q83689634 +Q1130557 +Q4922530 +Q107094905