See 種子島 in All languages combined, or Wiktionary
Download JSON data for 種子島 meaning in Japanese (9.7kB)
{
"etymology_templates": [
{
"args": {
"1": "ja",
"2": "種",
"3": "が",
"4": "島",
"pos2": "ancient genitive or possessive particle",
"sort": "たねがしま",
"t1": "seed",
"t3": "island",
"tr1": "tane",
"tr2": "ga",
"tr3": "shima"
},
"expansion": "種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”)",
"name": "compound"
},
{
"args": {
"1": "ja",
"2": "種子"
},
"expansion": "種子",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "熟字訓"
},
"expansion": "熟字訓",
"name": "m"
},
{
"args": {
"sort": "たねがしま"
},
"expansion": "jukujikun (熟字訓)",
"name": "juku"
},
{
"args": {
"nodots": "1"
},
"expansion": "CE",
"name": "C.E."
},
{
"args": {},
"expansion": "CE",
"name": "CE"
},
{
"args": {
"1": "ja",
"2": "多禰嶋"
},
"expansion": "多禰嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "",
"3": "多禰",
"tr": "tane"
},
"expansion": "多禰 (tane)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種",
"3": "",
"4": "seed",
"tr": "tane"
},
"expansion": "種 (tane, “seed”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "嶋"
},
"expansion": "嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "島",
"3": "",
"4": "island",
"tr": "shima"
},
"expansion": "島 (shima, “island”)",
"name": "m"
},
{
"args": {
"1": "en",
"2": "matchlock"
},
"expansion": "matchlock",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島銃",
"lit": "Tanegashima gun",
"tr": "Tanegashima jū"
},
"expansion": "種子島銃 (Tanegashima jū, literally “Tanegashima gun”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島鉄砲",
"lit": "Tanegashima cannon",
"tr": "Tanegashima teppō"
},
"expansion": "種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”)",
"name": "m"
}
],
"etymology_text": "Analyzable as a compound of 種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”).\nThe 種子 spelling for the tane portion is an example of jukujikun (熟字訓), using the spelling from a Chinese-derived synonym.\nFirst mentioned in the Nihon Shoki of 720 CE with the spelling 多禰嶋, where 多禰 (tane) appears to be a phonetic spelling of 種 (tane, “seed”), and 嶋 is an alternative form of 島 (shima, “island”).\nThe matchlock sense arose as an abbreviation of either 種子島銃 (Tanegashima jū, literally “Tanegashima gun”) or 種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”), which names arose due to matchlocks first being imported to Japan by the Portuguese in 1543, via the island of Tanegashima.\nThis sense is first cited to a text from 1607, but it was likely in use before this date.",
"forms": [
{
"form": "種子島",
"ruby": [
[
"種子島",
"たねがしま"
]
],
"tags": [
"canonical"
]
},
{
"form": "tanegashima",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "たねがしま"
},
"expansion": "種子島(たねがしま) • (tanegashima)",
"name": "ja-noun"
}
],
"lang": "Japanese",
"lang_code": "ja",
"pos": "noun",
"senses": [
{
"glosses": [
"種が島: matchlock"
],
"id": "en-種子島-ja-noun-tkXGSU-o",
"links": [
[
"種が島",
"種が島#Japanese"
],
[
"matchlock",
"matchlock"
]
],
"synonyms": [
{
"word": "火縄銃"
},
{
"word": "種子島銃"
},
{
"word": "種子島鉄砲"
}
]
},
{
"glosses": [
"a kind of fragrant aloeswood used for incense"
],
"id": "en-種子島-ja-noun-7caMxLid",
"links": [
[
"fragrant",
"fragrant"
],
[
"aloeswood",
"aloeswood"
],
[
"incense",
"incense"
]
]
},
{
"categories": [
{
"kind": "other",
"name": "Japanese terms with non-redundant non-automated sortkeys",
"parents": [
"Terms with non-redundant non-automated sortkeys",
"Entry maintenance"
],
"source": "w"
},
{
"_dis": "14 20 2 18 46",
"kind": "other",
"name": "Japanese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "22 22 1 16 38",
"kind": "other",
"name": "Japanese links with redundant wikilinks",
"parents": [
"Links with redundant wikilinks",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "23 22 1 16 38",
"kind": "other",
"name": "Japanese terms with non-redundant non-automated sortkeys",
"parents": [
"Terms with non-redundant non-automated sortkeys",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "22 22 1 17 38",
"kind": "other",
"name": "Japanese terms with redundant sortkeys",
"parents": [
"Terms with redundant sortkeys",
"Entry maintenance"
],
"source": "w+disamb"
}
],
"glosses": [
"fugu (so named for the way that poorly-prepared fugu is deadly, like a matchlock)"
],
"id": "en-種子島-ja-noun-HYOfrD4t",
"links": [
[
"fugu",
"fugu"
],
[
"deadly",
"deadly"
]
],
"raw_glosses": [
"(slang, archaic) fugu (so named for the way that poorly-prepared fugu is deadly, like a matchlock)"
],
"synonyms": [
{
"word": "河豚"
},
{
"word": "鉄砲"
}
],
"tags": [
"archaic",
"slang"
]
}
],
"sounds": [
{
"other": "たねがしま"
},
{
"ipa": "[ta̠ne̞ɡa̠ɕima̠]"
}
],
"wikipedia": [
"Daijisen",
"Nihon Shoki",
"Shogakukan",
"Tanegashima",
"Tanegashima (gun)",
"Tōkyō",
"ja:大辞泉",
"ja:松村明",
"ja:種子島"
],
"word": "種子島"
}
{
"etymology_templates": [
{
"args": {
"1": "ja",
"2": "種",
"3": "が",
"4": "島",
"pos2": "ancient genitive or possessive particle",
"sort": "たねがしま",
"t1": "seed",
"t3": "island",
"tr1": "tane",
"tr2": "ga",
"tr3": "shima"
},
"expansion": "種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”)",
"name": "compound"
},
{
"args": {
"1": "ja",
"2": "種子"
},
"expansion": "種子",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "熟字訓"
},
"expansion": "熟字訓",
"name": "m"
},
{
"args": {
"sort": "たねがしま"
},
"expansion": "jukujikun (熟字訓)",
"name": "juku"
},
{
"args": {
"nodots": "1"
},
"expansion": "CE",
"name": "C.E."
},
{
"args": {},
"expansion": "CE",
"name": "CE"
},
{
"args": {
"1": "ja",
"2": "多禰嶋"
},
"expansion": "多禰嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "",
"3": "多禰",
"tr": "tane"
},
"expansion": "多禰 (tane)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種",
"3": "",
"4": "seed",
"tr": "tane"
},
"expansion": "種 (tane, “seed”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "嶋"
},
"expansion": "嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "島",
"3": "",
"4": "island",
"tr": "shima"
},
"expansion": "島 (shima, “island”)",
"name": "m"
},
{
"args": {
"1": "en",
"2": "matchlock"
},
"expansion": "matchlock",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島銃",
"lit": "Tanegashima gun",
"tr": "Tanegashima jū"
},
"expansion": "種子島銃 (Tanegashima jū, literally “Tanegashima gun”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島鉄砲",
"lit": "Tanegashima cannon",
"tr": "Tanegashima teppō"
},
"expansion": "種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”)",
"name": "m"
}
],
"etymology_text": "Analyzable as a compound of 種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”).\nThe 種子 spelling for the tane portion is an example of jukujikun (熟字訓), using the spelling from a Chinese-derived synonym.\nFirst mentioned in the Nihon Shoki of 720 CE with the spelling 多禰嶋, where 多禰 (tane) appears to be a phonetic spelling of 種 (tane, “seed”), and 嶋 is an alternative form of 島 (shima, “island”).\nThe matchlock sense arose as an abbreviation of either 種子島銃 (Tanegashima jū, literally “Tanegashima gun”) or 種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”), which names arose due to matchlocks first being imported to Japan by the Portuguese in 1543, via the island of Tanegashima.\nThis sense is first cited to a text from 1607, but it was likely in use before this date.",
"forms": [
{
"form": "種子島",
"ruby": [
[
"種子島",
"たねがしま"
]
],
"tags": [
"canonical"
]
},
{
"form": "Tanegashima",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "proper",
"2": "たねがしま"
},
"expansion": "種子島(たねがしま) • (Tanegashima)",
"name": "ja-pos"
}
],
"lang": "Japanese",
"lang_code": "ja",
"pos": "name",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Japanese terms with non-redundant non-automated sortkeys",
"parents": [
"Terms with non-redundant non-automated sortkeys",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "place",
"langcode": "ja",
"name": "Islands",
"orig": "ja:Islands",
"parents": [
"Places",
"Names",
"All topics",
"Proper nouns",
"Terms by semantic function",
"Fundamental",
"Nouns",
"Lemmas"
],
"source": "w"
},
{
"kind": "place",
"langcode": "ja",
"name": "Places in Japan",
"orig": "ja:Places in Japan",
"parents": [
"Places",
"Names",
"All topics",
"Proper nouns",
"Terms by semantic function",
"Fundamental",
"Nouns",
"Lemmas"
],
"source": "w"
},
{
"kind": "place",
"langcode": "ja",
"name": "Places in Kagoshima Prefecture",
"orig": "ja:Places in Kagoshima Prefecture",
"parents": [
"Places",
"Names",
"All topics",
"Proper nouns",
"Terms by semantic function",
"Fundamental",
"Nouns",
"Lemmas"
],
"source": "w"
}
],
"glosses": [
"多禰島, 多禰嶋: Tanegashima (an island in Kagoshima Prefecture)"
],
"id": "en-種子島-ja-name-KBKiQEuf",
"links": [
[
"多禰島",
"多禰島#Japanese"
],
[
"多禰嶋",
"多禰嶋#Japanese"
],
[
"Tanegashima",
"Tanegashima#English"
],
[
"Kagoshima",
"Kagoshima#English"
]
]
},
{
"categories": [
{
"kind": "other",
"name": "Japanese surnames",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Japanese terms with non-redundant non-automated sortkeys",
"parents": [
"Terms with non-redundant non-automated sortkeys",
"Entry maintenance"
],
"source": "w"
}
],
"glosses": [
"a surname"
],
"id": "en-種子島-ja-name-v2O7m9sM",
"links": [
[
"surname",
"surname"
]
]
}
],
"sounds": [
{
"other": "たねがしま"
},
{
"ipa": "[ta̠ne̞ɡa̠ɕima̠]"
}
],
"wikipedia": [
"Daijisen",
"Nihon Shoki",
"Shogakukan",
"Tanegashima",
"Tanegashima (gun)",
"Tōkyō",
"ja:大辞泉",
"ja:松村明",
"ja:種子島"
],
"word": "種子島"
}
{
"categories": [
"Japanese compound terms",
"Japanese entries with incorrect language header",
"Japanese lemmas",
"Japanese links with redundant wikilinks",
"Japanese nouns",
"Japanese proper nouns",
"Japanese terms spelled with first grade kanji",
"Japanese terms spelled with fourth grade kanji",
"Japanese terms spelled with jukujikun",
"Japanese terms spelled with third grade kanji",
"Japanese terms with IPA pronunciation",
"Japanese terms with non-redundant non-automated sortkeys",
"Japanese terms with redundant sortkeys",
"Japanese terms written with three Han script characters"
],
"etymology_templates": [
{
"args": {
"1": "ja",
"2": "種",
"3": "が",
"4": "島",
"pos2": "ancient genitive or possessive particle",
"sort": "たねがしま",
"t1": "seed",
"t3": "island",
"tr1": "tane",
"tr2": "ga",
"tr3": "shima"
},
"expansion": "種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”)",
"name": "compound"
},
{
"args": {
"1": "ja",
"2": "種子"
},
"expansion": "種子",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "熟字訓"
},
"expansion": "熟字訓",
"name": "m"
},
{
"args": {
"sort": "たねがしま"
},
"expansion": "jukujikun (熟字訓)",
"name": "juku"
},
{
"args": {
"nodots": "1"
},
"expansion": "CE",
"name": "C.E."
},
{
"args": {},
"expansion": "CE",
"name": "CE"
},
{
"args": {
"1": "ja",
"2": "多禰嶋"
},
"expansion": "多禰嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "",
"3": "多禰",
"tr": "tane"
},
"expansion": "多禰 (tane)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種",
"3": "",
"4": "seed",
"tr": "tane"
},
"expansion": "種 (tane, “seed”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "嶋"
},
"expansion": "嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "島",
"3": "",
"4": "island",
"tr": "shima"
},
"expansion": "島 (shima, “island”)",
"name": "m"
},
{
"args": {
"1": "en",
"2": "matchlock"
},
"expansion": "matchlock",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島銃",
"lit": "Tanegashima gun",
"tr": "Tanegashima jū"
},
"expansion": "種子島銃 (Tanegashima jū, literally “Tanegashima gun”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島鉄砲",
"lit": "Tanegashima cannon",
"tr": "Tanegashima teppō"
},
"expansion": "種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”)",
"name": "m"
}
],
"etymology_text": "Analyzable as a compound of 種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”).\nThe 種子 spelling for the tane portion is an example of jukujikun (熟字訓), using the spelling from a Chinese-derived synonym.\nFirst mentioned in the Nihon Shoki of 720 CE with the spelling 多禰嶋, where 多禰 (tane) appears to be a phonetic spelling of 種 (tane, “seed”), and 嶋 is an alternative form of 島 (shima, “island”).\nThe matchlock sense arose as an abbreviation of either 種子島銃 (Tanegashima jū, literally “Tanegashima gun”) or 種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”), which names arose due to matchlocks first being imported to Japan by the Portuguese in 1543, via the island of Tanegashima.\nThis sense is first cited to a text from 1607, but it was likely in use before this date.",
"forms": [
{
"form": "種子島",
"ruby": [
[
"種子島",
"たねがしま"
]
],
"tags": [
"canonical"
]
},
{
"form": "tanegashima",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "たねがしま"
},
"expansion": "種子島(たねがしま) • (tanegashima)",
"name": "ja-noun"
}
],
"lang": "Japanese",
"lang_code": "ja",
"pos": "noun",
"senses": [
{
"glosses": [
"種が島: matchlock"
],
"links": [
[
"種が島",
"種が島#Japanese"
],
[
"matchlock",
"matchlock"
]
],
"synonyms": [
{
"word": "火縄銃"
},
{
"word": "種子島銃"
},
{
"word": "種子島鉄砲"
}
]
},
{
"glosses": [
"a kind of fragrant aloeswood used for incense"
],
"links": [
[
"fragrant",
"fragrant"
],
[
"aloeswood",
"aloeswood"
],
[
"incense",
"incense"
]
]
},
{
"categories": [
"Japanese slang",
"Japanese terms with archaic senses",
"Japanese terms with non-redundant non-automated sortkeys"
],
"glosses": [
"fugu (so named for the way that poorly-prepared fugu is deadly, like a matchlock)"
],
"links": [
[
"fugu",
"fugu"
],
[
"deadly",
"deadly"
]
],
"raw_glosses": [
"(slang, archaic) fugu (so named for the way that poorly-prepared fugu is deadly, like a matchlock)"
],
"synonyms": [
{
"word": "河豚"
},
{
"word": "鉄砲"
}
],
"tags": [
"archaic",
"slang"
]
}
],
"sounds": [
{
"other": "たねがしま"
},
{
"ipa": "[ta̠ne̞ɡa̠ɕima̠]"
}
],
"wikipedia": [
"Daijisen",
"Nihon Shoki",
"Shogakukan",
"Tanegashima",
"Tanegashima (gun)",
"Tōkyō",
"ja:大辞泉",
"ja:松村明",
"ja:種子島"
],
"word": "種子島"
}
{
"categories": [
"Japanese compound terms",
"Japanese entries with incorrect language header",
"Japanese lemmas",
"Japanese links with redundant wikilinks",
"Japanese nouns",
"Japanese proper nouns",
"Japanese terms spelled with first grade kanji",
"Japanese terms spelled with fourth grade kanji",
"Japanese terms spelled with jukujikun",
"Japanese terms spelled with third grade kanji",
"Japanese terms with IPA pronunciation",
"Japanese terms with non-redundant non-automated sortkeys",
"Japanese terms with redundant sortkeys",
"Japanese terms written with three Han script characters"
],
"etymology_templates": [
{
"args": {
"1": "ja",
"2": "種",
"3": "が",
"4": "島",
"pos2": "ancient genitive or possessive particle",
"sort": "たねがしま",
"t1": "seed",
"t3": "island",
"tr1": "tane",
"tr2": "ga",
"tr3": "shima"
},
"expansion": "種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”)",
"name": "compound"
},
{
"args": {
"1": "ja",
"2": "種子"
},
"expansion": "種子",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "熟字訓"
},
"expansion": "熟字訓",
"name": "m"
},
{
"args": {
"sort": "たねがしま"
},
"expansion": "jukujikun (熟字訓)",
"name": "juku"
},
{
"args": {
"nodots": "1"
},
"expansion": "CE",
"name": "C.E."
},
{
"args": {},
"expansion": "CE",
"name": "CE"
},
{
"args": {
"1": "ja",
"2": "多禰嶋"
},
"expansion": "多禰嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "",
"3": "多禰",
"tr": "tane"
},
"expansion": "多禰 (tane)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種",
"3": "",
"4": "seed",
"tr": "tane"
},
"expansion": "種 (tane, “seed”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "嶋"
},
"expansion": "嶋",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "島",
"3": "",
"4": "island",
"tr": "shima"
},
"expansion": "島 (shima, “island”)",
"name": "m"
},
{
"args": {
"1": "en",
"2": "matchlock"
},
"expansion": "matchlock",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島銃",
"lit": "Tanegashima gun",
"tr": "Tanegashima jū"
},
"expansion": "種子島銃 (Tanegashima jū, literally “Tanegashima gun”)",
"name": "m"
},
{
"args": {
"1": "ja",
"2": "種子島鉄砲",
"lit": "Tanegashima cannon",
"tr": "Tanegashima teppō"
},
"expansion": "種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”)",
"name": "m"
}
],
"etymology_text": "Analyzable as a compound of 種 (tane, “seed”) + が (ga, ancient genitive or possessive particle) + 島 (shima, “island”).\nThe 種子 spelling for the tane portion is an example of jukujikun (熟字訓), using the spelling from a Chinese-derived synonym.\nFirst mentioned in the Nihon Shoki of 720 CE with the spelling 多禰嶋, where 多禰 (tane) appears to be a phonetic spelling of 種 (tane, “seed”), and 嶋 is an alternative form of 島 (shima, “island”).\nThe matchlock sense arose as an abbreviation of either 種子島銃 (Tanegashima jū, literally “Tanegashima gun”) or 種子島鉄砲 (Tanegashima teppō, literally “Tanegashima cannon”), which names arose due to matchlocks first being imported to Japan by the Portuguese in 1543, via the island of Tanegashima.\nThis sense is first cited to a text from 1607, but it was likely in use before this date.",
"forms": [
{
"form": "種子島",
"ruby": [
[
"種子島",
"たねがしま"
]
],
"tags": [
"canonical"
]
},
{
"form": "Tanegashima",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "proper",
"2": "たねがしま"
},
"expansion": "種子島(たねがしま) • (Tanegashima)",
"name": "ja-pos"
}
],
"lang": "Japanese",
"lang_code": "ja",
"pos": "name",
"senses": [
{
"categories": [
"Japanese terms with non-redundant non-automated sortkeys",
"ja:Islands",
"ja:Places in Japan",
"ja:Places in Kagoshima Prefecture"
],
"glosses": [
"多禰島, 多禰嶋: Tanegashima (an island in Kagoshima Prefecture)"
],
"links": [
[
"多禰島",
"多禰島#Japanese"
],
[
"多禰嶋",
"多禰嶋#Japanese"
],
[
"Tanegashima",
"Tanegashima#English"
],
[
"Kagoshima",
"Kagoshima#English"
]
]
},
{
"categories": [
"Japanese surnames",
"Japanese terms with non-redundant non-automated sortkeys"
],
"glosses": [
"a surname"
],
"links": [
[
"surname",
"surname"
]
]
}
],
"sounds": [
{
"other": "たねがしま"
},
{
"ipa": "[ta̠ne̞ɡa̠ɕima̠]"
}
],
"wikipedia": [
"Daijisen",
"Nihon Shoki",
"Shogakukan",
"Tanegashima",
"Tanegashima (gun)",
"Tōkyō",
"ja:大辞泉",
"ja:松村明",
"ja:種子島"
],
"word": "種子島"
}
This page is a part of the kaikki.org machine-readable Japanese dictionary. This dictionary is based on structured data extracted on 2024-05-10 from the enwiktionary dump dated 2024-05-02 using wiktextract (a644e18 and edd475d). 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.