See sewage in All languages combined, or Wiktionary
{
"derived": [
{
"_dis1": "0 0",
"word": "raw sewage"
},
{
"_dis1": "0 0",
"word": "sewage fungus"
},
{
"_dis1": "0 0",
"word": "sewage plant"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "sewer",
"3": "age",
"gloss1": "system of pipes used to remove human waste and to provide drainage"
},
"expansion": "sewer (“system of pipes used to remove human waste and to provide drainage”) + -age",
"name": "suffix"
}
],
"etymology_text": "From sewer (“system of pipes used to remove human waste and to provide drainage”) + -age or from sew (“to drain or draw off water”) + -age.",
"forms": [
{
"form": "sewages",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "~"
},
"expansion": "sewage (countable and uncountable, plural sewages)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"_dis1": "0 0",
"word": "slop"
},
{
"_dis1": "0 0",
"word": "sludge"
},
{
"_dis1": "0 0",
"word": "sewer system"
},
{
"_dis1": "0 0",
"word": "sewage treatment"
},
{
"_dis1": "0 0",
"word": "waste management"
}
],
"senses": [
{
"categories": [
{
"_dis": "96 4",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "88 12",
"kind": "other",
"name": "English terms suffixed with -age",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "94 6",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "95 5",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Azerbaijani translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Bulgarian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Catalan translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "91 9",
"kind": "other",
"name": "Terms with Czech translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Dutch translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Esperanto translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Finnish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "93 7",
"kind": "other",
"name": "Terms with French translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with German translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Greek translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "93 7",
"kind": "other",
"name": "Terms with Ido translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Indonesian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Irish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Italian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Japanese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Macedonian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Malay translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Malayalam translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Mandarin translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Maori translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Navajo translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Persian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "90 10",
"kind": "other",
"name": "Terms with Polish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "91 9",
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Russian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "96 4",
"kind": "other",
"name": "Terms with Spanish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "89 11",
"kind": "other",
"name": "Terms with Swahili translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Swedish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "92 8",
"kind": "other",
"name": "Terms with Turkish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "97 3",
"kind": "topical",
"langcode": "en",
"name": "Water",
"orig": "en:Water",
"parents": [
"Liquids",
"Matter",
"Chemistry",
"Nature",
"Sciences",
"All topics",
"Fundamental"
],
"source": "w+disamb"
}
],
"glosses": [
"A suspension of water and solid waste, transported by sewers to be disposed of or processed."
],
"id": "en-sewage-en-noun-qkh0tHlB",
"links": [
[
"suspension",
"suspension"
],
[
"waste",
"waste"
],
[
"sewer",
"sewer"
],
[
"dispose",
"dispose"
],
[
"process",
"process"
]
],
"tags": [
"countable",
"uncountable"
],
"translations": [
{
"_dis1": "99 1",
"code": "az",
"lang": "Azerbaijani",
"sense": "suspension of water and waste",
"word": "lağım"
},
{
"_dis1": "99 1",
"code": "az",
"lang": "Azerbaijani",
"sense": "suspension of water and waste",
"word": "gəndov"
},
{
"_dis1": "99 1",
"code": "bg",
"lang": "Bulgarian",
"roman": "kanalni vodi",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "канални води"
},
{
"_dis1": "99 1",
"code": "ca",
"lang": "Catalan",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "aigües negres"
},
{
"_dis1": "99 1",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "wūshuǐ",
"sense": "suspension of water and waste",
"word": "污水"
},
{
"_dis1": "99 1",
"code": "cs",
"lang": "Czech",
"sense": "suspension of water and waste",
"tags": [
"masculine",
"plural"
],
"word": "splašky"
},
{
"_dis1": "99 1",
"code": "nl",
"lang": "Dutch",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "afvalwater"
},
{
"_dis1": "99 1",
"code": "nl",
"lang": "Dutch",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "rioolwater"
},
{
"_dis1": "99 1",
"code": "eo",
"lang": "Esperanto",
"sense": "suspension of water and waste",
"word": "rubakvo"
},
{
"_dis1": "99 1",
"code": "eo",
"lang": "Esperanto",
"sense": "suspension of water and waste",
"word": "kloakaĵo"
},
{
"_dis1": "99 1",
"code": "fi",
"lang": "Finnish",
"sense": "suspension of water and waste",
"word": "jätevesi"
},
{
"_dis1": "99 1",
"code": "fr",
"lang": "French",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "eaux usées"
},
{
"_dis1": "99 1",
"code": "de",
"lang": "German",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "Abwasser"
},
{
"_dis1": "99 1",
"code": "el",
"lang": "Greek",
"roman": "lýmata",
"sense": "suspension of water and waste",
"tags": [
"neuter",
"plural"
],
"word": "λύματα"
},
{
"_dis1": "99 1",
"code": "io",
"lang": "Ido",
"sense": "suspension of water and waste",
"word": "kloakajo"
},
{
"_dis1": "99 1",
"code": "id",
"lang": "Indonesian",
"sense": "suspension of water and waste",
"word": "air limbah"
},
{
"_dis1": "99 1",
"code": "ga",
"lang": "Irish",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "múnlach"
},
{
"_dis1": "99 1",
"code": "it",
"lang": "Italian",
"sense": "suspension of water and waste",
"word": "liquame"
},
{
"_dis1": "99 1",
"alt": "おすい",
"code": "ja",
"lang": "Japanese",
"roman": "osui",
"sense": "suspension of water and waste",
"word": "汚水"
},
{
"_dis1": "99 1",
"code": "mk",
"lang": "Macedonian",
"roman": "kanalizácija",
"sense": "suspension of water and waste",
"tags": [
"feminine"
],
"word": "канализа́ција"
},
{
"_dis1": "99 1",
"code": "ms",
"lang": "Malay",
"sense": "suspension of water and waste",
"word": "kumbahan"
},
{
"_dis1": "99 1",
"code": "ml",
"lang": "Malayalam",
"roman": "malinajalaṁ",
"sense": "suspension of water and waste",
"word": "മലിനജലം"
},
{
"_dis1": "99 1",
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "wai parakaingaki"
},
{
"_dis1": "99 1",
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "parakaingaki"
},
{
"_dis1": "99 1",
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "waihawa"
},
{
"_dis1": "99 1",
"code": "nv",
"lang": "Navajo",
"sense": "suspension of water and waste",
"word": "tóchxǫ́ʼį́"
},
{
"_dis1": "99 1",
"code": "nv",
"lang": "Navajo",
"sense": "suspension of water and waste",
"word": "tóchxǫ́ʼí"
},
{
"_dis1": "99 1",
"code": "fa",
"lang": "Persian",
"roman": "gandâb",
"sense": "suspension of water and waste",
"word": "گنداب"
},
{
"_dis1": "99 1",
"code": "pl",
"lang": "Polish",
"sense": "suspension of water and waste",
"tags": [
"masculine",
"plural"
],
"word": "ścieki"
},
{
"_dis1": "99 1",
"code": "pt",
"lang": "Portuguese",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "esgoto"
},
{
"_dis1": "99 1",
"code": "ru",
"lang": "Russian",
"roman": "stóčnyje vódy",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "сто́чные во́ды"
},
{
"_dis1": "99 1",
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "aguas residuales"
},
{
"_dis1": "99 1",
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"feminine"
],
"word": "agua cloacal"
},
{
"_dis1": "99 1",
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "lodo cloacal"
},
{
"_dis1": "99 1",
"code": "sw",
"lang": "Swahili",
"sense": "suspension of water and waste",
"word": "maji taka"
},
{
"_dis1": "99 1",
"code": "sv",
"lang": "Swedish",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "avloppsvatten"
},
{
"_dis1": "99 1",
"code": "tr",
"lang": "Turkish",
"sense": "suspension of water and waste",
"word": "lağım"
},
{
"_dis1": "99 1",
"code": "tr",
"lang": "Turkish",
"sense": "suspension of water and waste",
"word": "atık su"
}
]
},
{
"categories": [],
"glosses": [
"sewerage."
],
"id": "en-sewage-en-noun-0-9xAlHX",
"links": [
[
"sewerage",
"sewerage"
]
],
"raw_glosses": [
"(obsolete) sewerage."
],
"tags": [
"countable",
"obsolete",
"uncountable"
]
}
],
"sounds": [
{
"ipa": "/ˈsuː.ɪd͡ʒ/",
"tags": [
"Received-Pronunciation"
]
},
{
"ipa": "/ˈsu.ɪd͡ʒ/",
"tags": [
"General-American"
]
},
{
"audio": "LL-Q1860 (eng)-Vealhurl-sewage.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/3/36/LL-Q1860_%28eng%29-Vealhurl-sewage.wav/LL-Q1860_%28eng%29-Vealhurl-sewage.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/3/36/LL-Q1860_%28eng%29-Vealhurl-sewage.wav/LL-Q1860_%28eng%29-Vealhurl-sewage.wav.ogg"
},
{
"rhymes": "-uːɪdʒ"
}
],
"synonyms": [
{
"_dis1": "0 0",
"word": "wastewater"
}
],
"wikipedia": [
"sewage"
],
"word": "sewage"
}
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English nouns",
"English terms suffixed with -age",
"English uncountable nouns",
"Entries with translation boxes",
"Pages with 1 entry",
"Pages with entries",
"Rhymes:English/uːɪdʒ",
"Rhymes:English/uːɪdʒ/2 syllables",
"Terms with Azerbaijani translations",
"Terms with Bulgarian translations",
"Terms with Catalan translations",
"Terms with Czech translations",
"Terms with Dutch translations",
"Terms with Esperanto translations",
"Terms with Finnish translations",
"Terms with French translations",
"Terms with German translations",
"Terms with Greek translations",
"Terms with Ido translations",
"Terms with Indonesian translations",
"Terms with Irish translations",
"Terms with Italian translations",
"Terms with Japanese translations",
"Terms with Macedonian translations",
"Terms with Malay translations",
"Terms with Malayalam translations",
"Terms with Mandarin translations",
"Terms with Maori translations",
"Terms with Navajo translations",
"Terms with Persian translations",
"Terms with Polish translations",
"Terms with Portuguese translations",
"Terms with Russian translations",
"Terms with Spanish translations",
"Terms with Swahili translations",
"Terms with Swedish translations",
"Terms with Turkish translations",
"en:Water"
],
"derived": [
{
"word": "raw sewage"
},
{
"word": "sewage fungus"
},
{
"word": "sewage plant"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "sewer",
"3": "age",
"gloss1": "system of pipes used to remove human waste and to provide drainage"
},
"expansion": "sewer (“system of pipes used to remove human waste and to provide drainage”) + -age",
"name": "suffix"
}
],
"etymology_text": "From sewer (“system of pipes used to remove human waste and to provide drainage”) + -age or from sew (“to drain or draw off water”) + -age.",
"forms": [
{
"form": "sewages",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "~"
},
"expansion": "sewage (countable and uncountable, plural sewages)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "slop"
},
{
"word": "sludge"
},
{
"word": "sewer system"
},
{
"word": "sewage treatment"
},
{
"word": "waste management"
}
],
"senses": [
{
"glosses": [
"A suspension of water and solid waste, transported by sewers to be disposed of or processed."
],
"links": [
[
"suspension",
"suspension"
],
[
"waste",
"waste"
],
[
"sewer",
"sewer"
],
[
"dispose",
"dispose"
],
[
"process",
"process"
]
],
"tags": [
"countable",
"uncountable"
]
},
{
"categories": [
"English terms with obsolete senses"
],
"glosses": [
"sewerage."
],
"links": [
[
"sewerage",
"sewerage"
]
],
"raw_glosses": [
"(obsolete) sewerage."
],
"tags": [
"countable",
"obsolete",
"uncountable"
]
}
],
"sounds": [
{
"ipa": "/ˈsuː.ɪd͡ʒ/",
"tags": [
"Received-Pronunciation"
]
},
{
"ipa": "/ˈsu.ɪd͡ʒ/",
"tags": [
"General-American"
]
},
{
"audio": "LL-Q1860 (eng)-Vealhurl-sewage.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/3/36/LL-Q1860_%28eng%29-Vealhurl-sewage.wav/LL-Q1860_%28eng%29-Vealhurl-sewage.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/3/36/LL-Q1860_%28eng%29-Vealhurl-sewage.wav/LL-Q1860_%28eng%29-Vealhurl-sewage.wav.ogg"
},
{
"rhymes": "-uːɪdʒ"
}
],
"synonyms": [
{
"word": "wastewater"
}
],
"translations": [
{
"code": "az",
"lang": "Azerbaijani",
"sense": "suspension of water and waste",
"word": "lağım"
},
{
"code": "az",
"lang": "Azerbaijani",
"sense": "suspension of water and waste",
"word": "gəndov"
},
{
"code": "bg",
"lang": "Bulgarian",
"roman": "kanalni vodi",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "канални води"
},
{
"code": "ca",
"lang": "Catalan",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "aigües negres"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "wūshuǐ",
"sense": "suspension of water and waste",
"word": "污水"
},
{
"code": "cs",
"lang": "Czech",
"sense": "suspension of water and waste",
"tags": [
"masculine",
"plural"
],
"word": "splašky"
},
{
"code": "nl",
"lang": "Dutch",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "afvalwater"
},
{
"code": "nl",
"lang": "Dutch",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "rioolwater"
},
{
"code": "eo",
"lang": "Esperanto",
"sense": "suspension of water and waste",
"word": "rubakvo"
},
{
"code": "eo",
"lang": "Esperanto",
"sense": "suspension of water and waste",
"word": "kloakaĵo"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "suspension of water and waste",
"word": "jätevesi"
},
{
"code": "fr",
"lang": "French",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "eaux usées"
},
{
"code": "de",
"lang": "German",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "Abwasser"
},
{
"code": "el",
"lang": "Greek",
"roman": "lýmata",
"sense": "suspension of water and waste",
"tags": [
"neuter",
"plural"
],
"word": "λύματα"
},
{
"code": "io",
"lang": "Ido",
"sense": "suspension of water and waste",
"word": "kloakajo"
},
{
"code": "id",
"lang": "Indonesian",
"sense": "suspension of water and waste",
"word": "air limbah"
},
{
"code": "ga",
"lang": "Irish",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "múnlach"
},
{
"code": "it",
"lang": "Italian",
"sense": "suspension of water and waste",
"word": "liquame"
},
{
"alt": "おすい",
"code": "ja",
"lang": "Japanese",
"roman": "osui",
"sense": "suspension of water and waste",
"word": "汚水"
},
{
"code": "mk",
"lang": "Macedonian",
"roman": "kanalizácija",
"sense": "suspension of water and waste",
"tags": [
"feminine"
],
"word": "канализа́ција"
},
{
"code": "ms",
"lang": "Malay",
"sense": "suspension of water and waste",
"word": "kumbahan"
},
{
"code": "ml",
"lang": "Malayalam",
"roman": "malinajalaṁ",
"sense": "suspension of water and waste",
"word": "മലിനജലം"
},
{
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "wai parakaingaki"
},
{
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "parakaingaki"
},
{
"code": "mi",
"lang": "Maori",
"sense": "suspension of water and waste",
"word": "waihawa"
},
{
"code": "nv",
"lang": "Navajo",
"sense": "suspension of water and waste",
"word": "tóchxǫ́ʼį́"
},
{
"code": "nv",
"lang": "Navajo",
"sense": "suspension of water and waste",
"word": "tóchxǫ́ʼí"
},
{
"code": "fa",
"lang": "Persian",
"roman": "gandâb",
"sense": "suspension of water and waste",
"word": "گنداب"
},
{
"code": "pl",
"lang": "Polish",
"sense": "suspension of water and waste",
"tags": [
"masculine",
"plural"
],
"word": "ścieki"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "esgoto"
},
{
"code": "ru",
"lang": "Russian",
"roman": "stóčnyje vódy",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "сто́чные во́ды"
},
{
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"feminine",
"plural"
],
"word": "aguas residuales"
},
{
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"feminine"
],
"word": "agua cloacal"
},
{
"code": "es",
"lang": "Spanish",
"sense": "suspension of water and waste",
"tags": [
"masculine"
],
"word": "lodo cloacal"
},
{
"code": "sw",
"lang": "Swahili",
"sense": "suspension of water and waste",
"word": "maji taka"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "suspension of water and waste",
"tags": [
"neuter"
],
"word": "avloppsvatten"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "suspension of water and waste",
"word": "lağım"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "suspension of water and waste",
"word": "atık su"
}
],
"wikipedia": [
"sewage"
],
"word": "sewage"
}
Download raw JSONL data for sewage meaning in English (7.7kB)
This page is a part of the kaikki.org machine-readable English dictionary. This dictionary is based on structured data extracted on 2024-11-06 from the enwiktionary dump dated 2024-10-02 using wiktextract (fbeafe8 and 7f03c9b). 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.