See thôn on Wiktionary
Download JSONL data for thôn meaning in All languages combined (5.3kB)
{
"etymology_templates": [
{
"args": {
"1": "ace",
"2": "poz-pro",
"3": "*taqun"
},
"expansion": "Proto-Malayo-Polynesian *taqun",
"name": "inh"
},
{
"args": {
"1": "id",
"2": "tahun"
},
"expansion": "Indonesian tahun",
"name": "cog"
}
],
"etymology_text": "From Proto-Malayo-Polynesian *taqun. Compare Indonesian tahun.",
"head_templates": [
{
"args": {
"1": "ace",
"2": "noun"
},
"expansion": "thôn",
"name": "head"
}
],
"lang": "Acehnese",
"lang_code": "ace",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Acehnese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
}
],
"glosses": [
"year"
],
"id": "en-thôn-ace-noun-TLTqJVg8",
"links": [
[
"year",
"year"
]
]
}
],
"word": "thôn"
}
{
"etymology_templates": [
{
"args": {
"1": "mtq",
"2": "zh",
"3": "-"
},
"expansion": "Chinese",
"name": "bor"
},
{
"args": {
"1": "孫"
},
"expansion": "孫 (MC swon)",
"name": "ltc-l"
}
],
"etymology_text": "From Chinese 孫 (MC swon).\nDisplaced chảu, which now means \"son-in-law\".",
"head_templates": [
{
"args": {
"1": "mtq",
"2": "noun",
"head": "",
"sc": "Latn",
"sort": "",
"tr": ""
},
"expansion": "thôn",
"name": "head"
},
{
"args": {},
"expansion": "thôn",
"name": "mtq-noun"
}
],
"lang": "Muong",
"lang_code": "mtq",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Muong entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Muong terms with redundant script codes",
"parents": [
"Terms with redundant script codes",
"Entry maintenance"
],
"source": "w"
}
],
"examples": [
{
"english": "a grandson",
"text": "thôn tửa",
"type": "example"
}
],
"glosses": [
"grandchild"
],
"id": "en-thôn-mtq-noun-cTtPGPDh",
"links": [
[
"grandchild",
"grandchild"
]
],
"raw_glosses": [
"(Mường Bi) grandchild"
]
}
],
"sounds": [
{
"ipa": "/tʰon¹/"
}
],
"word": "thôn"
}
{
"etymology_templates": [
{
"args": {
"1": "vi",
"2": "Sino-Vietnamese words"
},
"expansion": "",
"name": "categorize"
},
{
"args": {
"1": "村"
},
"expansion": "Sino-Vietnamese word from 村",
"name": "vi-etym-sino"
}
],
"etymology_text": "Sino-Vietnamese word from 村.",
"head_templates": [
{
"args": {
"1": "vi",
"2": "noun",
"3": "",
"4": "",
"head": "",
"tr": ""
},
"expansion": "thôn",
"name": "head"
},
{
"args": {},
"expansion": "thôn",
"name": "vi-noun"
}
],
"lang": "Vietnamese",
"lang_code": "vi",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Northern Vietnamese",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Sino-Vietnamese words",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Vietnamese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Vietnamese nouns without classifiers",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Vietnamese terms with redundant script codes",
"parents": [
"Terms with redundant script codes",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "place",
"langcode": "vi",
"name": "Villages",
"orig": "vi:Villages",
"parents": [
"Polities",
"Places",
"Names",
"All topics",
"Proper nouns",
"Terms by semantic function",
"Fundamental",
"Nouns",
"Lemmas"
],
"source": "w"
}
],
"derived": [
{
"alt": "孤村",
"word": "cô thôn"
},
{
"alt": "鄉村",
"word": "hương thôn"
},
{
"alt": "农村",
"word": "nông thôn"
},
{
"alt": "村邑",
"word": "thôn ấp"
},
{
"word": "thôn bản"
},
{
"alt": "村野",
"word": "thôn dã"
},
{
"alt": "村民",
"word": "thôn dân"
},
{
"word": "thôn hương"
},
{
"word": "thôn nữ"
},
{
"word": "thôn ổ"
},
{
"word": "thôn quê"
},
{
"alt": "村莊",
"word": "thôn trang"
},
{
"word": "thôn trưởng"
},
{
"word": "thôn xã"
},
{
"word": "thôn xóm"
},
{
"word": "trưởng thôn"
},
{
"word": "xóm thôn"
}
],
"glosses": [
"a village"
],
"id": "en-thôn-vi-noun-lCSD8AEV",
"links": [
[
"village",
"village"
]
],
"raw_glosses": [
"(especially Northern Vietnam) a village"
],
"related": [
{
"word": "làng"
},
{
"word": "xóm"
}
],
"tags": [
"Northern",
"Vietnam",
"especially"
],
"wikipedia": [
"en:Subdivisions of Vietnam",
"vi:thôn"
]
}
],
"sounds": [
{
"ipa": "[tʰon˧˧]",
"tags": [
"Hà-Nội"
]
},
{
"ipa": "[tʰoŋ˧˧]",
"tags": [
"Huế"
]
},
{
"ipa": "[tʰoŋ˧˧]",
"note": "Saigon"
}
],
"word": "thôn"
}
{
"forms": [
{
"form": "no-table-tags",
"source": "mutation",
"tags": [
"table-tags"
]
},
{
"form": "cy-mut",
"source": "mutation",
"tags": [
"inflection-template"
]
},
{
"form": "tôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-radical"
]
},
{
"form": "dôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-soft"
]
},
{
"form": "nhôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-nasal"
]
},
{
"form": "thôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-aspirate"
]
}
],
"head_templates": [
{
"args": {
"1": "cy",
"2": "mutated noun"
},
"expansion": "thôn",
"name": "head"
}
],
"inflection_templates": [
{
"args": {
"1": "tôn"
},
"name": "cy-mut"
}
],
"lang": "Welsh",
"lang_code": "cy",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Welsh entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
}
],
"form_of": [
{
"word": "tôn"
}
],
"glosses": [
"Aspirate mutation of tôn."
],
"id": "en-thôn-cy-noun-m7sFdpaE",
"links": [
[
"tôn",
"tôn#Welsh"
]
],
"tags": [
"form-of",
"mutation-aspirate"
]
}
],
"sounds": [
{
"ipa": "/θoːn/"
}
],
"word": "thôn"
}
{
"etymology_templates": [
{
"args": {
"1": "ace",
"2": "poz-pro",
"3": "*taqun"
},
"expansion": "Proto-Malayo-Polynesian *taqun",
"name": "inh"
},
{
"args": {
"1": "id",
"2": "tahun"
},
"expansion": "Indonesian tahun",
"name": "cog"
}
],
"etymology_text": "From Proto-Malayo-Polynesian *taqun. Compare Indonesian tahun.",
"head_templates": [
{
"args": {
"1": "ace",
"2": "noun"
},
"expansion": "thôn",
"name": "head"
}
],
"lang": "Acehnese",
"lang_code": "ace",
"pos": "noun",
"senses": [
{
"categories": [
"Acehnese entries with incorrect language header",
"Acehnese lemmas",
"Acehnese nouns",
"Acehnese terms derived from Proto-Malayo-Polynesian",
"Acehnese terms inherited from Proto-Malayo-Polynesian"
],
"glosses": [
"year"
],
"links": [
[
"year",
"year"
]
]
}
],
"word": "thôn"
}
{
"etymology_templates": [
{
"args": {
"1": "mtq",
"2": "zh",
"3": "-"
},
"expansion": "Chinese",
"name": "bor"
},
{
"args": {
"1": "孫"
},
"expansion": "孫 (MC swon)",
"name": "ltc-l"
}
],
"etymology_text": "From Chinese 孫 (MC swon).\nDisplaced chảu, which now means \"son-in-law\".",
"head_templates": [
{
"args": {
"1": "mtq",
"2": "noun",
"head": "",
"sc": "Latn",
"sort": "",
"tr": ""
},
"expansion": "thôn",
"name": "head"
},
{
"args": {},
"expansion": "thôn",
"name": "mtq-noun"
}
],
"lang": "Muong",
"lang_code": "mtq",
"pos": "noun",
"senses": [
{
"categories": [
"Muong entries with incorrect language header",
"Muong lemmas",
"Muong nouns",
"Muong terms borrowed from Chinese",
"Muong terms derived from Chinese",
"Muong terms with IPA pronunciation",
"Muong terms with redundant script codes",
"Muong terms with usage examples"
],
"examples": [
{
"english": "a grandson",
"text": "thôn tửa",
"type": "example"
}
],
"glosses": [
"grandchild"
],
"links": [
[
"grandchild",
"grandchild"
]
],
"raw_glosses": [
"(Mường Bi) grandchild"
]
}
],
"sounds": [
{
"ipa": "/tʰon¹/"
}
],
"word": "thôn"
}
{
"derived": [
{
"alt": "孤村",
"word": "cô thôn"
},
{
"alt": "鄉村",
"word": "hương thôn"
},
{
"alt": "农村",
"word": "nông thôn"
},
{
"alt": "村邑",
"word": "thôn ấp"
},
{
"word": "thôn bản"
},
{
"alt": "村野",
"word": "thôn dã"
},
{
"alt": "村民",
"word": "thôn dân"
},
{
"word": "thôn hương"
},
{
"word": "thôn nữ"
},
{
"word": "thôn ổ"
},
{
"word": "thôn quê"
},
{
"alt": "村莊",
"word": "thôn trang"
},
{
"word": "thôn trưởng"
},
{
"word": "thôn xã"
},
{
"word": "thôn xóm"
},
{
"word": "trưởng thôn"
},
{
"word": "xóm thôn"
}
],
"etymology_templates": [
{
"args": {
"1": "vi",
"2": "Sino-Vietnamese words"
},
"expansion": "",
"name": "categorize"
},
{
"args": {
"1": "村"
},
"expansion": "Sino-Vietnamese word from 村",
"name": "vi-etym-sino"
}
],
"etymology_text": "Sino-Vietnamese word from 村.",
"head_templates": [
{
"args": {
"1": "vi",
"2": "noun",
"3": "",
"4": "",
"head": "",
"tr": ""
},
"expansion": "thôn",
"name": "head"
},
{
"args": {},
"expansion": "thôn",
"name": "vi-noun"
}
],
"lang": "Vietnamese",
"lang_code": "vi",
"pos": "noun",
"related": [
{
"word": "làng"
},
{
"word": "xóm"
}
],
"senses": [
{
"categories": [
"Northern Vietnamese",
"Sino-Vietnamese words",
"Vietnamese entries with incorrect language header",
"Vietnamese lemmas",
"Vietnamese nouns",
"Vietnamese nouns without classifiers",
"Vietnamese terms with IPA pronunciation",
"Vietnamese terms with redundant script codes",
"vi:Villages"
],
"glosses": [
"a village"
],
"links": [
[
"village",
"village"
]
],
"raw_glosses": [
"(especially Northern Vietnam) a village"
],
"tags": [
"Northern",
"Vietnam",
"especially"
],
"wikipedia": [
"en:Subdivisions of Vietnam",
"vi:thôn"
]
}
],
"sounds": [
{
"ipa": "[tʰon˧˧]",
"tags": [
"Hà-Nội"
]
},
{
"ipa": "[tʰoŋ˧˧]",
"tags": [
"Huế"
]
},
{
"ipa": "[tʰoŋ˧˧]",
"note": "Saigon"
}
],
"word": "thôn"
}
{
"forms": [
{
"form": "no-table-tags",
"source": "mutation",
"tags": [
"table-tags"
]
},
{
"form": "cy-mut",
"source": "mutation",
"tags": [
"inflection-template"
]
},
{
"form": "tôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-radical"
]
},
{
"form": "dôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-soft"
]
},
{
"form": "nhôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-nasal"
]
},
{
"form": "thôn",
"source": "mutation",
"tags": [
"mutation",
"mutation-aspirate"
]
}
],
"head_templates": [
{
"args": {
"1": "cy",
"2": "mutated noun"
},
"expansion": "thôn",
"name": "head"
}
],
"inflection_templates": [
{
"args": {
"1": "tôn"
},
"name": "cy-mut"
}
],
"lang": "Welsh",
"lang_code": "cy",
"pos": "noun",
"senses": [
{
"categories": [
"Welsh aspirate-mutation forms",
"Welsh entries with incorrect language header",
"Welsh mutated nouns",
"Welsh non-lemma forms",
"Welsh terms with IPA pronunciation"
],
"form_of": [
{
"word": "tôn"
}
],
"glosses": [
"Aspirate mutation of tôn."
],
"links": [
[
"tôn",
"tôn#Welsh"
]
],
"tags": [
"form-of",
"mutation-aspirate"
]
}
],
"sounds": [
{
"ipa": "/θoːn/"
}
],
"word": "thôn"
}
{
"called_from": "form_descriptions/1831",
"msg": "unrecognized sense qualifier: Mường Bi",
"path": [
"thôn"
],
"section": "Muong",
"subsection": "noun",
"title": "thôn",
"trace": ""
}
{
"called_from": "form_descriptions/1831",
"msg": "unrecognized sense qualifier: Mường Bi",
"path": [
"thôn"
],
"section": "Muong",
"subsection": "noun",
"title": "thôn",
"trace": ""
}
{
"called_from": "inflection/2522",
"msg": "rejected heuristic header: table cell identified as header based on style, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Welsh]; cleaned text: tôn, style: padding-bottom:4px;////NodeKind.TABLE_CELL",
"path": [
"thôn"
],
"section": "Welsh",
"subsection": "noun",
"title": "thôn",
"trace": ""
}
{
"called_from": "inflection/2522",
"msg": "rejected heuristic header: table cell identified as header based on style, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Welsh]; cleaned text: dôn, style: padding-bottom:4px;////NodeKind.TABLE_CELL",
"path": [
"thôn"
],
"section": "Welsh",
"subsection": "noun",
"title": "thôn",
"trace": ""
}
{
"called_from": "inflection/2522",
"msg": "rejected heuristic header: table cell identified as header based on style, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Welsh]; cleaned text: nhôn, style: padding-bottom:4px;////NodeKind.TABLE_CELL",
"path": [
"thôn"
],
"section": "Welsh",
"subsection": "noun",
"title": "thôn",
"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 2024-06-27 from the enwiktionary dump dated 2024-06-20 using wiktextract (0f7b3ac and b863ecc). 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.