See corpus in All languages combined, or Wiktionary
{
"etymology_templates": [
{
"args": {
"1": "fr",
"2": ":ubor",
"3": "la:corpus<t:body>"
},
"expansion": "[Appendix:Glossary#unadapted_borrowing|Unadapted borrowing]] from\", \"terms\" : [ { \"gloss\" : \"body\", \"children\" : [ { \"terms\" : [ { \"id\" : \"body\", \"children\" : [ { \"keyword_abbrev\" : \"der.\", \"keyword_label\" : \"Derived from\", \"terms\" : [ { \"id\" : \"body\", \"children\" : [ ], \"status\" : \"ok\", \"lang_name\" : \"Proto-Indo-European\", \"term\" : \"*krep-\", \"lang\" : \"ine-pro\" } ], \"keyword\" : \"derived\" } ], \"status\" : \"ok\", \"lang_name\" : \"Proto-Italic\", \"term\" : \"*korpos\", \"lang\" : \"itc-pro\" } ], \"keyword_label\" : \"Inherited from\", \"keyword\" : \"inherited\" } ], \"lang_name\" : \"Latin\", \"term\" : \"corpus\", \"status\" : \"ok\", \"lang\" : \"la\" } ], \"keyword\" : \"ubor\" } ], \"lang_name\" : \"French\", \"term\" : \"corpus\", \"status\" : \"ok\", \"lang\" : \"fr\" }\" data-lang=\"fr\" data-title=\"corpus\">",
"name": "ety"
},
{
"args": {
"1": "fr",
"2": "la",
"3": "corpus",
"4": "",
"5": "body"
},
"expansion": "Unadapted borrowing from Latin corpus (“body”)",
"name": "ubor"
},
{
"args": {
"1": "fr",
"2": "corps"
},
"expansion": "Doublet of corps",
"name": "doublet"
}
],
"etymology_text": "Unadapted borrowing from Latin corpus (“body”). Doublet of corps.",
"head_templates": [
{
"args": {
"1": "m"
},
"expansion": "corpus m (invariable)",
"name": "fr-noun"
}
],
"lang": "French",
"lang_code": "fr",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "French entries with etymon",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "French entries with incorrect language header",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages using etymon with no ID",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 10 entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with etymon",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "fr",
"name": "Linguistics",
"orig": "fr:Linguistics",
"parents": [],
"source": "w"
}
],
"glosses": [
"a corpus, a body of texts"
],
"id": "en-corpus-fr-noun-C4UFfPS5",
"links": [
[
"linguistics",
"linguistics"
],
[
"corpus",
"corpus#English"
],
[
"body",
"body"
],
[
"text",
"text"
]
],
"raw_glosses": [
"(linguistics) a corpus, a body of texts"
],
"tags": [
"invariable",
"masculine"
],
"topics": [
"human-sciences",
"linguistics",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/kɔʁ.pys/"
},
{
"audio": "LL-Q150 (fra)-LoquaxFR-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/a/ab/LL-Q150_%28fra%29-LoquaxFR-corpus.wav/LL-Q150_%28fra%29-LoquaxFR-corpus.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/a/ab/LL-Q150_%28fra%29-LoquaxFR-corpus.wav/LL-Q150_%28fra%29-LoquaxFR-corpus.wav.ogg",
"tags": [
"France",
"Vosges"
]
},
{
"audio": "LL-Q150 (fra)-WikiLucas00-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/2/28/LL-Q150_%28fra%29-WikiLucas00-corpus.wav/LL-Q150_%28fra%29-WikiLucas00-corpus.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/2/28/LL-Q150_%28fra%29-WikiLucas00-corpus.wav/LL-Q150_%28fra%29-WikiLucas00-corpus.wav.ogg",
"tags": [
"France",
"Lyon"
]
},
{
"audio": "LL-Q150 (fra)-Eihel-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/c/c8/LL-Q150_%28fra%29-Eihel-corpus.wav/LL-Q150_%28fra%29-Eihel-corpus.wav.mp3",
"note": "Lausanne",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/c/c8/LL-Q150_%28fra%29-Eihel-corpus.wav/LL-Q150_%28fra%29-Eihel-corpus.wav.ogg",
"tags": [
"Switzerland"
]
}
],
"word": "corpus"
}
{
"etymology_templates": [
{
"args": {
"1": "fr",
"2": ":ubor",
"3": "la:corpus<t:body>"
},
"expansion": "[Appendix:Glossary#unadapted_borrowing|Unadapted borrowing]] from\", \"terms\" : [ { \"gloss\" : \"body\", \"children\" : [ { \"terms\" : [ { \"id\" : \"body\", \"children\" : [ { \"keyword_abbrev\" : \"der.\", \"keyword_label\" : \"Derived from\", \"terms\" : [ { \"id\" : \"body\", \"children\" : [ ], \"status\" : \"ok\", \"lang_name\" : \"Proto-Indo-European\", \"term\" : \"*krep-\", \"lang\" : \"ine-pro\" } ], \"keyword\" : \"derived\" } ], \"status\" : \"ok\", \"lang_name\" : \"Proto-Italic\", \"term\" : \"*korpos\", \"lang\" : \"itc-pro\" } ], \"keyword_label\" : \"Inherited from\", \"keyword\" : \"inherited\" } ], \"lang_name\" : \"Latin\", \"term\" : \"corpus\", \"status\" : \"ok\", \"lang\" : \"la\" } ], \"keyword\" : \"ubor\" } ], \"lang_name\" : \"French\", \"term\" : \"corpus\", \"status\" : \"ok\", \"lang\" : \"fr\" }\" data-lang=\"fr\" data-title=\"corpus\">",
"name": "ety"
},
{
"args": {
"1": "fr",
"2": "la",
"3": "corpus",
"4": "",
"5": "body"
},
"expansion": "Unadapted borrowing from Latin corpus (“body”)",
"name": "ubor"
},
{
"args": {
"1": "fr",
"2": "corps"
},
"expansion": "Doublet of corps",
"name": "doublet"
}
],
"etymology_text": "Unadapted borrowing from Latin corpus (“body”). Doublet of corps.",
"head_templates": [
{
"args": {
"1": "m"
},
"expansion": "corpus m (invariable)",
"name": "fr-noun"
}
],
"lang": "French",
"lang_code": "fr",
"pos": "noun",
"senses": [
{
"categories": [
"French 2-syllable words",
"French countable nouns",
"French doublets",
"French entries with etymon",
"French entries with incorrect language header",
"French indeclinable nouns",
"French lemmas",
"French masculine nouns",
"French nouns",
"French terms borrowed from Latin",
"French terms derived from Latin",
"French terms derived from Proto-Indo-European",
"French terms derived from Proto-Italic",
"French terms derived from the Proto-Indo-European root *krep-",
"French terms with IPA pronunciation",
"French unadapted borrowings from Latin",
"Pages using etymon with no ID",
"Pages with 10 entries",
"Pages with entries",
"Pages with etymon",
"fr:Linguistics"
],
"glosses": [
"a corpus, a body of texts"
],
"links": [
[
"linguistics",
"linguistics"
],
[
"corpus",
"corpus#English"
],
[
"body",
"body"
],
[
"text",
"text"
]
],
"raw_glosses": [
"(linguistics) a corpus, a body of texts"
],
"tags": [
"invariable",
"masculine"
],
"topics": [
"human-sciences",
"linguistics",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/kɔʁ.pys/"
},
{
"audio": "LL-Q150 (fra)-LoquaxFR-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/a/ab/LL-Q150_%28fra%29-LoquaxFR-corpus.wav/LL-Q150_%28fra%29-LoquaxFR-corpus.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/a/ab/LL-Q150_%28fra%29-LoquaxFR-corpus.wav/LL-Q150_%28fra%29-LoquaxFR-corpus.wav.ogg",
"tags": [
"France",
"Vosges"
]
},
{
"audio": "LL-Q150 (fra)-WikiLucas00-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/2/28/LL-Q150_%28fra%29-WikiLucas00-corpus.wav/LL-Q150_%28fra%29-WikiLucas00-corpus.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/2/28/LL-Q150_%28fra%29-WikiLucas00-corpus.wav/LL-Q150_%28fra%29-WikiLucas00-corpus.wav.ogg",
"tags": [
"France",
"Lyon"
]
},
{
"audio": "LL-Q150 (fra)-Eihel-corpus.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/c/c8/LL-Q150_%28fra%29-Eihel-corpus.wav/LL-Q150_%28fra%29-Eihel-corpus.wav.mp3",
"note": "Lausanne",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/c/c8/LL-Q150_%28fra%29-Eihel-corpus.wav/LL-Q150_%28fra%29-Eihel-corpus.wav.ogg",
"tags": [
"Switzerland"
]
}
],
"word": "corpus"
}
Download raw JSONL data for corpus meaning in French (3.6kB)
This page is a part of the kaikki.org machine-readable French dictionary. This dictionary is based on structured data extracted on 2026-08-28 from the enwiktionary dump dated 2026-08-05 using wiktextract (872fc7b and 4deed51). 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.