See taen on Wiktionary
{ "head_templates": [ { "args": { "1": "adl", "2": "noun" }, "expansion": "taen", "name": "head" } ], "lang": "Galo", "lang_code": "adl", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Galo entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "31 37 25 2 6", "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w+disamb" }, { "_dis": "30 36 24 1 8", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "cowry shell" ], "id": "en-taen-adl-noun-FjMLZDjg", "links": [ [ "cowry", "cowry" ], [ "shell", "shell" ] ] } ], "word": "taen" } { "etymology_templates": [ { "args": { "1": "ga", "2": "gem-pro", "3": "ine-pro" }, "expansion": "", "name": "dercat" }, { "args": { "1": "ga", "2": "enm", "3": "theyn" }, "expansion": "Middle English theyn", "name": "der" }, { "args": { "1": "ga", "2": "ang", "3": "þæġn" }, "expansion": "Old English þæġn", "name": "der" }, { "args": { "1": "ga", "2": "gmw-pro", "3": "*þegn", "t": "man, warrior" }, "expansion": "Proto-West Germanic *þegn (“man, warrior”)", "name": "der" } ], "etymology_text": "From Middle English theyn, from Old English þæġn, þeġen, þeġn, from Proto-West Germanic *þegn (“man, warrior”).", "forms": [ { "form": "taein", "tags": [ "genitive", "singular" ] }, { "form": "taein", "tags": [ "nominative", "plural" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "cln", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "nominative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "taen", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "taein", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "vocative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "a thaein", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "a thaena", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "genitive", "source": "declension", "tags": [ "indefinite" ] }, { "form": "taein", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "taen", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "dative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "cln", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "nominative", "source": "declension", "tags": [ "definite" ] }, { "form": "an taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "na taein", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "genitive", "source": "declension", "tags": [ "definite" ] }, { "form": "an taein", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "na dtaen", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "dative", "source": "declension", "tags": [ "definite" ] }, { "form": "leis an taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "don taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "leis na taein", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "no-table-tags", "source": "mutation", "tags": [ "table-tags" ] }, { "form": "ga-mut", "source": "mutation", "tags": [ "inflection-template" ] }, { "form": "taen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "thaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "dtaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] } ], "head_templates": [ { "args": { "1": "ga", "10": "", "11": "nominative plural", "12": "taein", "13": "", "14": "", "15": "", "16": "", "2": "noun", "3": "genitive singular", "4": "taein", "5": "", "6": "", "7": "", "8": "", "9": "", "cat2": "", "f1request": "1", "f4request": "1", "g": "m", "g2": "", "g3": "", "head": "" }, "expansion": "taen m (genitive singular taein, nominative plural taein)", "name": "head" }, { "args": { "1": "m", "2": "taein", "3": "taein" }, "expansion": "taen m (genitive singular taein, nominative plural taein)", "name": "ga-noun" } ], "inflection_templates": [ { "args": {}, "name": "ga-mut" } ], "lang": "Irish", "lang_code": "ga", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Irish entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "31 37 25 2 6", "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w+disamb" }, { "_dis": "30 36 24 1 8", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "thane" ], "id": "en-taen-ga-noun-3kiVjlaw", "links": [ [ "thane", "thane" ] ], "raw_glosses": [ "(historical) thane" ], "tags": [ "historical", "masculine" ] } ], "word": "taen" } { "head_templates": [ { "args": { "1": "sco", "2": "past participle" }, "expansion": "taen", "name": "head" } ], "lang": "Scots", "lang_code": "sco", "pos": "verb", "senses": [ { "categories": [ { "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Scots entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "_dis": "31 37 25 2 6", "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w+disamb" }, { "_dis": "30 36 24 1 8", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "form_of": [ { "word": "tak" } ], "glosses": [ "past participle of tak" ], "id": "en-taen-sco-verb-0jB-Csv8", "links": [ [ "tak", "tak#Scots" ] ], "synonyms": [ { "word": "tane" }, { "word": "takken" } ], "tags": [ "form-of", "participle", "past" ] } ], "word": "taen" } { "etymology_number": 1, "etymology_templates": [ { "args": { "1": "cy", "2": "cel-bry-pro", "3": "*tagna" }, "expansion": "Proto-Brythonic *tagna", "name": "inh" }, { "args": { "1": "cy", "2": "ine-pro", "3": "*tn̥néwti", "t": "to be stretching" }, "expansion": "Proto-Indo-European *tn̥néwti (“to be stretching”)", "name": "der" } ], "etymology_text": "From Proto-Brythonic *tagna, from Proto-Indo-European *tn̥néwti (“to be stretching”).", "forms": [ { "form": "taenion", "tags": [ "plural" ] } ], "head_templates": [ { "args": { "1": "m", "2": "taenion" }, "expansion": "taen m (plural taenion)", "name": "cy-noun" } ], "lang": "Welsh", "lang_code": "cy", "pos": "noun", "senses": [ { "derived": [ { "english": "spread, spread out", "word": "ar daen" }, { "english": "sprinkle", "word": "taenell" }, { "english": "spreadsheet", "word": "taenlen" }, { "english": "to spread", "word": "taenu" } ], "glosses": [ "spreading, dispersion" ], "id": "en-taen-cy-noun-tYN8y~FX", "links": [ [ "spreading", "spreading" ], [ "dispersion", "dispersion" ] ], "tags": [ "masculine" ] } ], "sounds": [ { "ipa": "/taːɨ̯n/", "tags": [ "North-Wales" ] }, { "ipa": "/tai̯n/", "tags": [ "South-Wales" ] } ], "word": "taen" } { "etymology_number": 2, "etymology_text": "Inflected form of bod (“to be”).", "forms": [ { "form": "no-table-tags", "source": "mutation", "tags": [ "table-tags" ] }, { "form": "cy-mut", "source": "mutation", "tags": [ "inflection-template" ] }, { "form": "taen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "daen", "source": "mutation", "tags": [ "soft" ] }, { "form": "nhaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "thaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] } ], "head_templates": [ { "args": {}, "expansion": "taen", "name": "cy-verb form" } ], "inflection_templates": [ { "args": {}, "name": "cy-mut" } ], "lang": "Welsh", "lang_code": "cy", "pos": "verb", "senses": [ { "categories": [ { "_dis": "24 76", "kind": "other", "name": "Welsh entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "examples": [ { "english": "if we were happy", "text": "(pe) taen ni hapus", "type": "example" }, { "english": "if they were happy", "text": "(pe) taen nhw hapus", "type": "example" } ], "form_of": [ { "extra": "(used after pe (“if”), which can also be omitted)", "word": "bod" } ], "glosses": [ "first/third-person plural counterfactual conditional colloquial of bod (used after pe (“if”), which can also be omitted)" ], "id": "en-taen-cy-verb-P5XYcTze", "links": [ [ "bod", "bod#Welsh" ], [ "pe", "pe#Welsh" ] ], "tags": [ "colloquial", "conditional", "counterfactual", "first-person", "form-of", "plural", "third-person" ] } ], "sounds": [ { "ipa": "/taːɨ̯n/", "tags": [ "North-Wales" ] }, { "ipa": "/tai̯n/", "tags": [ "South-Wales" ] } ], "word": "taen" }
{ "categories": [ "Pages with 4 entries", "Pages with entries" ], "head_templates": [ { "args": { "1": "adl", "2": "noun" }, "expansion": "taen", "name": "head" } ], "lang": "Galo", "lang_code": "adl", "pos": "noun", "senses": [ { "categories": [ "Galo entries with incorrect language header", "Galo lemmas", "Galo nouns", "Pages with 4 entries", "Pages with entries" ], "glosses": [ "cowry shell" ], "links": [ [ "cowry", "cowry" ], [ "shell", "shell" ] ] } ], "word": "taen" } { "categories": [ "Pages with 4 entries", "Pages with entries" ], "etymology_templates": [ { "args": { "1": "ga", "2": "gem-pro", "3": "ine-pro" }, "expansion": "", "name": "dercat" }, { "args": { "1": "ga", "2": "enm", "3": "theyn" }, "expansion": "Middle English theyn", "name": "der" }, { "args": { "1": "ga", "2": "ang", "3": "þæġn" }, "expansion": "Old English þæġn", "name": "der" }, { "args": { "1": "ga", "2": "gmw-pro", "3": "*þegn", "t": "man, warrior" }, "expansion": "Proto-West Germanic *þegn (“man, warrior”)", "name": "der" } ], "etymology_text": "From Middle English theyn, from Old English þæġn, þeġen, þeġn, from Proto-West Germanic *þegn (“man, warrior”).", "forms": [ { "form": "taein", "tags": [ "genitive", "singular" ] }, { "form": "taein", "tags": [ "nominative", "plural" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "cln", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "nominative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "taen", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "taein", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "vocative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "a thaein", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "a thaena", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "genitive", "source": "declension", "tags": [ "indefinite" ] }, { "form": "taein", "source": "declension", "tags": [ "indefinite", "singular" ] }, { "form": "taen", "source": "declension", "tags": [ "indefinite", "plural" ] }, { "form": "dative", "source": "declension", "tags": [ "indefinite" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "cln", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "nominative", "source": "declension", "tags": [ "definite" ] }, { "form": "an taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "na taein", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "genitive", "source": "declension", "tags": [ "definite" ] }, { "form": "an taein", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "na dtaen", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "dative", "source": "declension", "tags": [ "definite" ] }, { "form": "leis an taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "don taen", "source": "declension", "tags": [ "definite", "singular" ] }, { "form": "leis na taein", "source": "declension", "tags": [ "definite", "plural" ] }, { "form": "no-table-tags", "source": "mutation", "tags": [ "table-tags" ] }, { "form": "ga-mut", "source": "mutation", "tags": [ "inflection-template" ] }, { "form": "taen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "thaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "dtaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] } ], "head_templates": [ { "args": { "1": "ga", "10": "", "11": "nominative plural", "12": "taein", "13": "", "14": "", "15": "", "16": "", "2": "noun", "3": "genitive singular", "4": "taein", "5": "", "6": "", "7": "", "8": "", "9": "", "cat2": "", "f1request": "1", "f4request": "1", "g": "m", "g2": "", "g3": "", "head": "" }, "expansion": "taen m (genitive singular taein, nominative plural taein)", "name": "head" }, { "args": { "1": "m", "2": "taein", "3": "taein" }, "expansion": "taen m (genitive singular taein, nominative plural taein)", "name": "ga-noun" } ], "inflection_templates": [ { "args": {}, "name": "ga-mut" } ], "lang": "Irish", "lang_code": "ga", "pos": "noun", "senses": [ { "categories": [ "Irish entries with incorrect language header", "Irish first-declension nouns", "Irish lemmas", "Irish masculine nouns", "Irish nouns", "Irish terms derived from Middle English", "Irish terms derived from Old English", "Irish terms derived from Proto-Germanic", "Irish terms derived from Proto-Indo-European", "Irish terms derived from Proto-West Germanic", "Irish terms with historical senses", "Pages with 4 entries", "Pages with entries" ], "glosses": [ "thane" ], "links": [ [ "thane", "thane" ] ], "raw_glosses": [ "(historical) thane" ], "tags": [ "historical", "masculine" ] } ], "word": "taen" } { "categories": [ "Pages with 4 entries", "Pages with entries" ], "head_templates": [ { "args": { "1": "sco", "2": "past participle" }, "expansion": "taen", "name": "head" } ], "lang": "Scots", "lang_code": "sco", "pos": "verb", "senses": [ { "categories": [ "Pages with 4 entries", "Pages with entries", "Scots entries with incorrect language header", "Scots non-lemma forms", "Scots past participles" ], "form_of": [ { "word": "tak" } ], "glosses": [ "past participle of tak" ], "links": [ [ "tak", "tak#Scots" ] ], "tags": [ "form-of", "participle", "past" ] } ], "synonyms": [ { "word": "tane" }, { "word": "takken" } ], "word": "taen" } { "categories": [ "Pages with 4 entries", "Pages with entries", "Welsh countable nouns", "Welsh entries with incorrect language header", "Welsh lemmas", "Welsh masculine nouns", "Welsh non-lemma forms", "Welsh nouns", "Welsh terms derived from Proto-Brythonic", "Welsh terms derived from Proto-Indo-European", "Welsh terms inherited from Proto-Brythonic", "Welsh verb forms" ], "derived": [ { "english": "spread, spread out", "word": "ar daen" }, { "english": "sprinkle", "word": "taenell" }, { "english": "spreadsheet", "word": "taenlen" }, { "english": "to spread", "word": "taenu" } ], "etymology_number": 1, "etymology_templates": [ { "args": { "1": "cy", "2": "cel-bry-pro", "3": "*tagna" }, "expansion": "Proto-Brythonic *tagna", "name": "inh" }, { "args": { "1": "cy", "2": "ine-pro", "3": "*tn̥néwti", "t": "to be stretching" }, "expansion": "Proto-Indo-European *tn̥néwti (“to be stretching”)", "name": "der" } ], "etymology_text": "From Proto-Brythonic *tagna, from Proto-Indo-European *tn̥néwti (“to be stretching”).", "forms": [ { "form": "taenion", "tags": [ "plural" ] } ], "head_templates": [ { "args": { "1": "m", "2": "taenion" }, "expansion": "taen m (plural taenion)", "name": "cy-noun" } ], "lang": "Welsh", "lang_code": "cy", "pos": "noun", "senses": [ { "glosses": [ "spreading, dispersion" ], "links": [ [ "spreading", "spreading" ], [ "dispersion", "dispersion" ] ], "tags": [ "masculine" ] } ], "sounds": [ { "ipa": "/taːɨ̯n/", "tags": [ "North-Wales" ] }, { "ipa": "/tai̯n/", "tags": [ "South-Wales" ] } ], "word": "taen" } { "categories": [ "Pages with 4 entries", "Pages with entries", "Welsh entries with incorrect language header", "Welsh non-lemma forms", "Welsh verb forms" ], "etymology_number": 2, "etymology_text": "Inflected form of bod (“to be”).", "forms": [ { "form": "no-table-tags", "source": "mutation", "tags": [ "table-tags" ] }, { "form": "cy-mut", "source": "mutation", "tags": [ "inflection-template" ] }, { "form": "taen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "daen", "source": "mutation", "tags": [ "soft" ] }, { "form": "nhaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] }, { "form": "thaen", "source": "mutation", "tags": [ "error-unrecognized-form" ] } ], "head_templates": [ { "args": {}, "expansion": "taen", "name": "cy-verb form" } ], "inflection_templates": [ { "args": {}, "name": "cy-mut" } ], "lang": "Welsh", "lang_code": "cy", "pos": "verb", "senses": [ { "categories": [ "Welsh colloquial verb forms", "Welsh terms with usage examples" ], "examples": [ { "english": "if we were happy", "text": "(pe) taen ni hapus", "type": "example" }, { "english": "if they were happy", "text": "(pe) taen nhw hapus", "type": "example" } ], "form_of": [ { "extra": "(used after pe (“if”), which can also be omitted)", "word": "bod" } ], "glosses": [ "first/third-person plural counterfactual conditional colloquial of bod (used after pe (“if”), which can also be omitted)" ], "links": [ [ "bod", "bod#Welsh" ], [ "pe", "pe#Welsh" ] ], "tags": [ "colloquial", "conditional", "counterfactual", "first-person", "form-of", "plural", "third-person" ] } ], "sounds": [ { "ipa": "/taːɨ̯n/", "tags": [ "North-Wales" ] }, { "ipa": "/tai̯n/", "tags": [ "South-Wales" ] } ], "word": "taen" }
Download raw JSONL data for taen meaning in All languages combined (8.3kB)
{ "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: nominative", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: vocative", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: genitive", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: dative", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: nominative", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: genitive", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/2457", "msg": "rejected heuristic header: table cell identified as header and given candidate status, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Irish]; cleaned text: dative", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/865", "msg": "inflection table: IF WITHOUT ELSE EVALS False: taen/Irish 'radical' base_tags=set()", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/735", "msg": "inflection table: unrecognized header: 'lenition'", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/735", "msg": "inflection table: unrecognized header: 'eclipsis'", "path": [ "taen" ], "section": "Irish", "subsection": "noun", "title": "taen", "trace": "" } { "called_from": "inflection/865", "msg": "inflection table: IF WITHOUT ELSE EVALS False: taen/Welsh 'radical' base_tags=set()", "path": [ "taen" ], "section": "Welsh", "subsection": "verb", "title": "taen", "trace": "" } { "called_from": "inflection/865", "msg": "inflection table: IF WITHOUT ELSE EVALS False: taen/Welsh 'nasal' base_tags={'soft', 'error-unrecognized-form'}", "path": [ "taen" ], "section": "Welsh", "subsection": "verb", "title": "taen", "trace": "" } { "called_from": "inflection/865", "msg": "inflection table: IF WITHOUT ELSE EVALS False: taen/Welsh 'aspirate' base_tags={'soft', 'error-unrecognized-form'}", "path": [ "taen" ], "section": "Welsh", "subsection": "verb", "title": "taen", "trace": "" }
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-12-15 from the enwiktionary dump dated 2024-12-04 using wiktextract (8a39820 and 4401a4c). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.