See mangsa on Wiktionary
{ "head_templates": [ { "args": { "1": "ban", "2": "romanization", "head": "", "sc": "Latn" }, "expansion": "mangsa", "name": "head" }, { "args": {}, "expansion": "mangsa", "name": "ban-rom" } ], "lang": "Balinese", "lang_code": "ban", "pos": "romanization", "senses": [ { "alt_of": [ { "word": "ᬫᬵᬗ᭄ᬲ" } ], "categories": [ { "_dis": "48 52", "kind": "other", "name": "Balinese entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "48 52", "kind": "other", "name": "Balinese romanizations", "parents": [], "source": "w+disamb" }, { "_dis": "46 54", "kind": "other", "name": "Balinese terms with redundant script codes", "parents": [ "Terms with redundant script codes", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "11 12 9 23 2 2 4 4 28 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "Romanization of ᬫᬵᬗ᭄ᬲ" ], "id": "en-mangsa-ban-romanization-BpKDhg9k", "links": [ [ "ᬫᬵᬗ᭄ᬲ", "ᬫᬵᬗ᭄ᬲ#Balinese" ] ], "tags": [ "alt-of", "romanization" ] }, { "alt_of": [ { "word": "ᬫᬗ᭄ᬲ" } ], "categories": [ { "_dis": "48 52", "kind": "other", "name": "Balinese entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "48 52", "kind": "other", "name": "Balinese romanizations", "parents": [], "source": "w+disamb" }, { "_dis": "46 54", "kind": "other", "name": "Balinese terms with redundant script codes", "parents": [ "Terms with redundant script codes", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "11 12 9 23 2 2 4 4 28 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "Romanization of ᬫᬗ᭄ᬲ" ], "id": "en-mangsa-ban-romanization-vglMJwnM", "links": [ [ "ᬫᬗ᭄ᬲ", "ᬫᬗ᭄ᬲ#Balinese" ] ], "tags": [ "alt-of", "romanization" ] } ], "word": "mangsa" } { "etymology_templates": [ { "args": { "1": "id", "2": "inh", "3": "ms>mangsa>victim", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa", "name": "etymon" }, { "args": { "1": "id", "2": "ms", "3": "mangsa", "t": "victim, corpse" }, "expansion": "Malay mangsa (“victim, corpse”)", "name": "inh" }, { "args": { "1": "id", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "der" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa\nFrom Malay mangsa (“victim, corpse”), from Sanskrit मांस (māṃsa, “flesh”).", "head_templates": [ { "args": { "1": "id", "2": "noun" }, "expansion": "mangsa", "name": "head" } ], "hyphenation": [ "mang‧sa" ], "lang": "Indonesian", "lang_code": "id", "pos": "noun", "senses": [ { "glosses": [ "prey", "that which is or may be seized by animals to be devoured." ], "id": "en-mangsa-id-noun-RULn53Rc", "links": [ [ "prey", "prey" ] ] }, { "categories": [ { "_dis": "11 12 9 23 2 2 4 4 28 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" }, { "_dis": "12 48 9 9 10 12", "kind": "other", "name": "Indonesian entries with etymology trees", "parents": [ "Entries with etymology trees", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "14 57 6 6 7 11", "kind": "other", "name": "Indonesian entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "glosses": [ "prey", "a person or thing given up as a victim." ], "id": "en-mangsa-id-noun-jpFkPZqV", "links": [ [ "prey", "prey" ] ] }, { "glosses": [ "prey", "a living thing, usually an animal, that is eaten by another living thing." ], "id": "en-mangsa-id-noun-py-azeXX", "links": [ [ "prey", "prey" ] ] }, { "categories": [], "glosses": [ "prey", "the victim of a disease." ], "id": "en-mangsa-id-noun-e6pRAp07", "links": [ [ "prey", "prey" ] ], "raw_glosses": [ "prey", "(rare) the victim of a disease." ], "tags": [ "rare" ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sa/" }, { "rhymes": "-sa" } ], "word": "mangsa" } { "derived": [ { "_dis1": "0 0", "word": "pemangsa" } ], "etymology_templates": [ { "args": { "1": "id", "2": "inh", "3": "ms>mangsa>victim", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa", "name": "etymon" }, { "args": { "1": "id", "2": "ms", "3": "mangsa", "t": "victim, corpse" }, "expansion": "Malay mangsa (“victim, corpse”)", "name": "inh" }, { "args": { "1": "id", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "der" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa\nFrom Malay mangsa (“victim, corpse”), from Sanskrit मांस (māṃsa, “flesh”).", "forms": [ { "form": "memangsa", "tags": [ "active" ] }, { "form": "dimangsa", "tags": [ "passive" ] } ], "head_templates": [ { "args": { "1": "id", "2": "verb", "3": "active", "4": "memangsa", "5": "passive", "6": "dimangsa" }, "expansion": "mangsa (active memangsa, passive dimangsa)", "name": "head" } ], "hyphenation": [ "mang‧sa" ], "lang": "Indonesian", "lang_code": "id", "pos": "verb", "senses": [ { "categories": [], "glosses": [ "to prey on", "to eat (as a predator)." ], "id": "en-mangsa-id-verb-exojkT09", "links": [ [ "prey on", "prey on" ], [ "eat", "eat" ], [ "predator", "predator" ] ], "raw_glosses": [ "(transitive) to prey on", "to eat (as a predator)." ], "tags": [ "transitive" ] }, { "categories": [], "glosses": [ "to prey on", "to exploit or victimize." ], "id": "en-mangsa-id-verb-zNW5h~tU", "links": [ [ "prey on", "prey on" ], [ "exploit", "exploit" ], [ "victimize", "victimize" ] ], "raw_glosses": [ "(transitive) to prey on", "(figuratively) to exploit or victimize." ], "tags": [ "figuratively", "transitive" ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sa/" }, { "rhymes": "-sa" } ], "word": "mangsa" } { "head_templates": [ { "args": { "1": "jv", "2": "romanization", "head": "", "sc": "Latn" }, "expansion": "mangsa", "name": "head" }, { "args": {}, "expansion": "mangsa", "name": "jv-rom" } ], "lang": "Javanese", "lang_code": "jv", "pos": "romanization", "senses": [ { "alt_of": [ { "word": "ꦩꦁꦱ" } ], "categories": [ { "kind": "other", "name": "Javanese entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Javanese romanizations", "parents": [], "source": "w" }, { "kind": "other", "name": "Javanese terms with redundant script codes", "parents": [ "Terms with redundant script codes", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "8 9 7 19 3 3 6 6 33 3 3", "kind": "other", "name": "Pages with 4 entries", "parents": [], "source": "w+disamb" }, { "_dis": "11 12 9 23 2 2 4 4 28 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "Romanization of ꦩꦁꦱ" ], "id": "en-mangsa-jv-romanization-MGqVjCwm", "links": [ [ "ꦩꦁꦱ", "ꦩꦁꦱ#Javanese" ] ], "tags": [ "alt-of", "romanization" ] } ], "word": "mangsa" } { "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "id", "2": "mangsa" }, "expansion": "Indonesian: mangsa", "name": "desc" } ], "text": "Indonesian: mangsa" } ], "etymology_templates": [ { "args": { "1": "ms", "2": "bor", "3": "sa>मांस>flesh", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa", "name": "etymon" }, { "args": { "1": "ms", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "bor" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nBorrowed from Sanskrit मांस (māṃsa, “flesh”).", "forms": [ { "form": "مڠسا", "tags": [ "Jawi" ] }, { "form": "mangsa-mangsa", "tags": [ "plural" ] }, { "form": "mangsaku", "tags": [ "first-person", "informal", "possessive" ] }, { "form": "mangsamu", "tags": [ "possessive", "second-person" ] }, { "form": "mangsanya", "tags": [ "possessive", "third-person" ] } ], "head_templates": [ { "args": { "j": "مڠسا" }, "expansion": "mangsa (Jawi spelling مڠسا, plural mangsa-mangsa, informal 1st possessive mangsaku, 2nd possessive mangsamu, 3rd possessive mangsanya)", "name": "ms-noun" } ], "lang": "Malay", "lang_code": "ms", "pos": "noun", "senses": [ { "categories": [ { "_dis": "53 47", "kind": "other", "name": "Malay entries with etymology trees", "parents": [ "Entries with etymology trees", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "51 49", "kind": "other", "name": "Malay entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "glosses": [ "victim" ], "id": "en-mangsa-ms-noun-G91bW5Li", "links": [ [ "victim", "victim" ] ] }, { "categories": [ { "_dis": "53 47", "kind": "other", "name": "Malay entries with etymology trees", "parents": [ "Entries with etymology trees", "Entry maintenance" ], "source": "w+disamb" }, { "_dis": "51 49", "kind": "other", "name": "Malay entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "glosses": [ "corpse" ], "id": "en-mangsa-ms-noun-QsdTlq8d", "links": [ [ "corpse", "corpse" ] ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sə/", "tags": [ "Johor-Selangor" ] }, { "ipa": "/ˈmaŋ.sa/", "tags": [ "Riau-Lingga" ] }, { "rhymes": "-aŋsə" }, { "rhymes": "-ŋsə" }, { "rhymes": "-sə" }, { "rhymes": "-ə" } ], "word": "mangsa" }
{ "categories": [ "Balinese entries with incorrect language header", "Balinese non-lemma forms", "Balinese romanizations", "Balinese terms with redundant script codes", "Pages with 4 entries", "Pages with entries" ], "head_templates": [ { "args": { "1": "ban", "2": "romanization", "head": "", "sc": "Latn" }, "expansion": "mangsa", "name": "head" }, { "args": {}, "expansion": "mangsa", "name": "ban-rom" } ], "lang": "Balinese", "lang_code": "ban", "pos": "romanization", "senses": [ { "alt_of": [ { "word": "ᬫᬵᬗ᭄ᬲ" } ], "glosses": [ "Romanization of ᬫᬵᬗ᭄ᬲ" ], "links": [ [ "ᬫᬵᬗ᭄ᬲ", "ᬫᬵᬗ᭄ᬲ#Balinese" ] ], "tags": [ "alt-of", "romanization" ] }, { "alt_of": [ { "word": "ᬫᬗ᭄ᬲ" } ], "glosses": [ "Romanization of ᬫᬗ᭄ᬲ" ], "links": [ [ "ᬫᬗ᭄ᬲ", "ᬫᬗ᭄ᬲ#Balinese" ] ], "tags": [ "alt-of", "romanization" ] } ], "word": "mangsa" } { "categories": [ "Indonesian entries with etymology trees", "Indonesian entries with incorrect language header", "Indonesian lemmas", "Indonesian nouns", "Indonesian terms derived from Malay", "Indonesian terms derived from Proto-Indo-European", "Indonesian terms derived from Proto-Indo-Iranian", "Indonesian terms derived from Sanskrit", "Indonesian terms derived from the Proto-Indo-European root *mems-", "Indonesian terms inherited from Malay", "Indonesian verbs", "Pages with 4 entries", "Pages with entries", "Rhymes:Indonesian/sa", "Rhymes:Indonesian/sa/2 syllables" ], "etymology_templates": [ { "args": { "1": "id", "2": "inh", "3": "ms>mangsa>victim", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa", "name": "etymon" }, { "args": { "1": "id", "2": "ms", "3": "mangsa", "t": "victim, corpse" }, "expansion": "Malay mangsa (“victim, corpse”)", "name": "inh" }, { "args": { "1": "id", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "der" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa\nFrom Malay mangsa (“victim, corpse”), from Sanskrit मांस (māṃsa, “flesh”).", "head_templates": [ { "args": { "1": "id", "2": "noun" }, "expansion": "mangsa", "name": "head" } ], "hyphenation": [ "mang‧sa" ], "lang": "Indonesian", "lang_code": "id", "pos": "noun", "senses": [ { "glosses": [ "prey", "that which is or may be seized by animals to be devoured." ], "links": [ [ "prey", "prey" ] ] }, { "glosses": [ "prey", "a person or thing given up as a victim." ], "links": [ [ "prey", "prey" ] ] }, { "glosses": [ "prey", "a living thing, usually an animal, that is eaten by another living thing." ], "links": [ [ "prey", "prey" ] ] }, { "categories": [ "Indonesian terms with rare senses" ], "glosses": [ "prey", "the victim of a disease." ], "links": [ [ "prey", "prey" ] ], "raw_glosses": [ "prey", "(rare) the victim of a disease." ], "tags": [ "rare" ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sa/" }, { "rhymes": "-sa" } ], "word": "mangsa" } { "categories": [ "Indonesian entries with etymology trees", "Indonesian entries with incorrect language header", "Indonesian lemmas", "Indonesian nouns", "Indonesian terms derived from Malay", "Indonesian terms derived from Proto-Indo-European", "Indonesian terms derived from Proto-Indo-Iranian", "Indonesian terms derived from Sanskrit", "Indonesian terms derived from the Proto-Indo-European root *mems-", "Indonesian terms inherited from Malay", "Indonesian verbs", "Pages with 4 entries", "Pages with entries", "Rhymes:Indonesian/sa", "Rhymes:Indonesian/sa/2 syllables" ], "derived": [ { "word": "pemangsa" } ], "etymology_templates": [ { "args": { "1": "id", "2": "inh", "3": "ms>mangsa>victim", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa", "name": "etymon" }, { "args": { "1": "id", "2": "ms", "3": "mangsa", "t": "victim, corpse" }, "expansion": "Malay mangsa (“victim, corpse”)", "name": "inh" }, { "args": { "1": "id", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "der" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nIndonesian mangsa\nFrom Malay mangsa (“victim, corpse”), from Sanskrit मांस (māṃsa, “flesh”).", "forms": [ { "form": "memangsa", "tags": [ "active" ] }, { "form": "dimangsa", "tags": [ "passive" ] } ], "head_templates": [ { "args": { "1": "id", "2": "verb", "3": "active", "4": "memangsa", "5": "passive", "6": "dimangsa" }, "expansion": "mangsa (active memangsa, passive dimangsa)", "name": "head" } ], "hyphenation": [ "mang‧sa" ], "lang": "Indonesian", "lang_code": "id", "pos": "verb", "senses": [ { "categories": [ "Indonesian transitive verbs" ], "glosses": [ "to prey on", "to eat (as a predator)." ], "links": [ [ "prey on", "prey on" ], [ "eat", "eat" ], [ "predator", "predator" ] ], "raw_glosses": [ "(transitive) to prey on", "to eat (as a predator)." ], "tags": [ "transitive" ] }, { "categories": [ "Indonesian transitive verbs" ], "glosses": [ "to prey on", "to exploit or victimize." ], "links": [ [ "prey on", "prey on" ], [ "exploit", "exploit" ], [ "victimize", "victimize" ] ], "raw_glosses": [ "(transitive) to prey on", "(figuratively) to exploit or victimize." ], "tags": [ "figuratively", "transitive" ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sa/" }, { "rhymes": "-sa" } ], "word": "mangsa" } { "categories": [ "Pages with 4 entries", "Pages with entries" ], "head_templates": [ { "args": { "1": "jv", "2": "romanization", "head": "", "sc": "Latn" }, "expansion": "mangsa", "name": "head" }, { "args": {}, "expansion": "mangsa", "name": "jv-rom" } ], "lang": "Javanese", "lang_code": "jv", "pos": "romanization", "senses": [ { "alt_of": [ { "word": "ꦩꦁꦱ" } ], "categories": [ "Javanese entries with incorrect language header", "Javanese non-lemma forms", "Javanese romanizations", "Javanese terms with redundant script codes", "Pages with 4 entries", "Pages with entries" ], "glosses": [ "Romanization of ꦩꦁꦱ" ], "links": [ [ "ꦩꦁꦱ", "ꦩꦁꦱ#Javanese" ] ], "tags": [ "alt-of", "romanization" ] } ], "word": "mangsa" } { "categories": [ "Malay entries with etymology trees", "Malay entries with incorrect language header", "Malay lemmas", "Malay nouns", "Malay terms borrowed from Sanskrit", "Malay terms derived from Proto-Indo-European", "Malay terms derived from Proto-Indo-Iranian", "Malay terms derived from Sanskrit", "Malay terms derived from the Proto-Indo-European root *mems-", "Pages with 4 entries", "Pages with entries", "Rhymes:Malay/aŋsə", "Rhymes:Malay/aŋsə/2 syllables", "Rhymes:Malay/sə", "Rhymes:Malay/sə/2 syllables", "Rhymes:Malay/ŋsə", "Rhymes:Malay/ŋsə/2 syllables", "Rhymes:Malay/ə", "Rhymes:Malay/ə/2 syllables" ], "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "id", "2": "mangsa" }, "expansion": "Indonesian: mangsa", "name": "desc" } ], "text": "Indonesian: mangsa" } ], "etymology_templates": [ { "args": { "1": "ms", "2": "bor", "3": "sa>मांस>flesh", "id": "victim", "tree": "1" }, "expansion": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa", "name": "etymon" }, { "args": { "1": "ms", "2": "sa", "3": "मांस", "t": "flesh" }, "expansion": "Sanskrit मांस (māṃsa, “flesh”)", "name": "bor" } ], "etymology_text": "Etymology tree\nProto-Indo-European *mems-\nProto-Indo-European *mḗmsder.\nProto-Indo-Iranian *māmsám\nSanskrit मांस (māṃsa)bor.\nMalay mangsa\nBorrowed from Sanskrit मांस (māṃsa, “flesh”).", "forms": [ { "form": "مڠسا", "tags": [ "Jawi" ] }, { "form": "mangsa-mangsa", "tags": [ "plural" ] }, { "form": "mangsaku", "tags": [ "first-person", "informal", "possessive" ] }, { "form": "mangsamu", "tags": [ "possessive", "second-person" ] }, { "form": "mangsanya", "tags": [ "possessive", "third-person" ] } ], "head_templates": [ { "args": { "j": "مڠسا" }, "expansion": "mangsa (Jawi spelling مڠسا, plural mangsa-mangsa, informal 1st possessive mangsaku, 2nd possessive mangsamu, 3rd possessive mangsanya)", "name": "ms-noun" } ], "lang": "Malay", "lang_code": "ms", "pos": "noun", "senses": [ { "glosses": [ "victim" ], "links": [ [ "victim", "victim" ] ] }, { "glosses": [ "corpse" ], "links": [ [ "corpse", "corpse" ] ] } ], "sounds": [ { "ipa": "/ˈmaŋ.sə/", "tags": [ "Johor-Selangor" ] }, { "ipa": "/ˈmaŋ.sa/", "tags": [ "Riau-Lingga" ] }, { "rhymes": "-aŋsə" }, { "rhymes": "-ŋsə" }, { "rhymes": "-sə" }, { "rhymes": "-ə" } ], "word": "mangsa" }
Download raw JSONL data for mangsa meaning in All languages combined (8.6kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2025-02-17 from the enwiktionary dump dated 2025-02-02 using wiktextract (ca09fec and c40eb85). 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.