See oum on Wiktionary
{
"head_templates": [
{
"args": {
"1": "njz",
"2": "numeral"
},
"expansion": "oum",
"name": "head"
}
],
"lang": "Nyishi",
"lang_code": "njz",
"pos": "num",
"senses": [
{
"categories": [
{
"kind": "topical",
"name": "Nyishi cardinal numbers",
"parents": [
"Cardinal numbers",
"Numbers",
"All topics",
"Terms by semantic function",
"Fundamental"
],
"source": "w"
},
{
"kind": "other",
"name": "Nyishi entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
}
],
"glosses": [
"three"
],
"id": "en-oum-njz-num-i1udsME9",
"links": [
[
"three",
"three"
]
],
"synonyms": [
{
"word": "om"
}
]
}
],
"word": "oum"
}
{
"etymology_templates": [
{
"args": {
"1": "pac",
"2": "mkh-kat-pro",
"3": "*ʔoom"
},
"expansion": "Proto-Katuic *ʔoom",
"name": "inh"
},
{
"args": {
"1": "pac",
"2": "mkh-pro",
"3": "-"
},
"expansion": "Proto-Mon-Khmer",
"name": "inh"
},
{
"args": {
"1": "bdq",
"2": "um"
},
"expansion": "Bahnar um",
"name": "cog"
},
{
"args": {
"1": "km",
"2": "អុំ"
},
"expansion": "Khmer អុំ (ʼom)",
"name": "cog"
},
{
"args": {
"1": "mtq",
"2": "-"
},
"expansion": "Muong",
"name": "cog"
},
{
"args": {
"1": "kjg",
"2": "-"
},
"expansion": "Khmu",
"name": "cog"
},
{
"args": {
"1": "mnw",
"2": "ဂုံ"
},
"expansion": "Mon ဂုံ",
"name": "cog"
},
{
"args": {
"1": "prk",
"2": "keem"
},
"expansion": "Parauk keem",
"name": "cog"
},
{
"args": {
"1": "sea",
"2": "geep"
},
"expansion": "Semai geep",
"name": "cog"
},
{
"args": {
"1": "scq",
"2": "-"
},
"expansion": "Sa'och",
"name": "cog"
},
{
"args": {
"1": "sat",
"2": "ᱜᱩᱢ"
},
"expansion": "Santali ᱜᱩᱢ (gum)",
"name": "cog"
}
],
"etymology_text": "From Proto-Katuic *ʔoom, from Proto-Mon-Khmer. Cognate with Bahnar um, Khmer អុំ (ʼom), Muong Bi củm, Khmu [Cuang] guːm, Mon ဂုံ, Parauk keem, Semai geep, Sa'och kṳːm, Santali ᱜᱩᱢ (gum).\nKatuic, Bahnaric and Khmer have zero-initial for this word, while all other branches have a velar stop.",
"head_templates": [
{
"args": {
"1": "pac",
"2": "verb",
"head": ""
},
"expansion": "oum",
"name": "head"
},
{
"args": {},
"expansion": "oum",
"name": "pac-verb"
}
],
"lang": "Pacoh",
"lang_code": "pac",
"pos": "verb",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Pacoh entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Parauk terms in nonstandard scripts",
"parents": [
"Terms in nonstandard scripts",
"Entry maintenance"
],
"source": "w"
}
],
"glosses": [
"to winnow grains"
],
"id": "en-oum-pac-verb-xhR1WZ85",
"links": [
[
"winnow",
"winnow"
],
[
"grain",
"grain"
]
],
"qualifier": "Tal-ay dialect",
"raw_glosses": [
"(Tal-ay dialect) to winnow grains"
],
"synonyms": [
{
"alt": "Kadô",
"word": "om"
}
]
}
],
"sounds": [
{
"ipa": "[ʔṵːm]"
}
],
"word": "oum"
}
{
"head_templates": [
{
"args": {
"1": "njz",
"2": "numeral"
},
"expansion": "oum",
"name": "head"
}
],
"lang": "Nyishi",
"lang_code": "njz",
"pos": "num",
"senses": [
{
"categories": [
"Nyishi cardinal numbers",
"Nyishi entries with incorrect language header",
"Nyishi lemmas",
"Nyishi numerals",
"Pages with 2 entries",
"Pages with entries"
],
"glosses": [
"three"
],
"links": [
[
"three",
"three"
]
]
}
],
"synonyms": [
{
"word": "om"
}
],
"word": "oum"
}
{
"etymology_templates": [
{
"args": {
"1": "pac",
"2": "mkh-kat-pro",
"3": "*ʔoom"
},
"expansion": "Proto-Katuic *ʔoom",
"name": "inh"
},
{
"args": {
"1": "pac",
"2": "mkh-pro",
"3": "-"
},
"expansion": "Proto-Mon-Khmer",
"name": "inh"
},
{
"args": {
"1": "bdq",
"2": "um"
},
"expansion": "Bahnar um",
"name": "cog"
},
{
"args": {
"1": "km",
"2": "អុំ"
},
"expansion": "Khmer អុំ (ʼom)",
"name": "cog"
},
{
"args": {
"1": "mtq",
"2": "-"
},
"expansion": "Muong",
"name": "cog"
},
{
"args": {
"1": "kjg",
"2": "-"
},
"expansion": "Khmu",
"name": "cog"
},
{
"args": {
"1": "mnw",
"2": "ဂုံ"
},
"expansion": "Mon ဂုံ",
"name": "cog"
},
{
"args": {
"1": "prk",
"2": "keem"
},
"expansion": "Parauk keem",
"name": "cog"
},
{
"args": {
"1": "sea",
"2": "geep"
},
"expansion": "Semai geep",
"name": "cog"
},
{
"args": {
"1": "scq",
"2": "-"
},
"expansion": "Sa'och",
"name": "cog"
},
{
"args": {
"1": "sat",
"2": "ᱜᱩᱢ"
},
"expansion": "Santali ᱜᱩᱢ (gum)",
"name": "cog"
}
],
"etymology_text": "From Proto-Katuic *ʔoom, from Proto-Mon-Khmer. Cognate with Bahnar um, Khmer អុំ (ʼom), Muong Bi củm, Khmu [Cuang] guːm, Mon ဂုံ, Parauk keem, Semai geep, Sa'och kṳːm, Santali ᱜᱩᱢ (gum).\nKatuic, Bahnaric and Khmer have zero-initial for this word, while all other branches have a velar stop.",
"head_templates": [
{
"args": {
"1": "pac",
"2": "verb",
"head": ""
},
"expansion": "oum",
"name": "head"
},
{
"args": {},
"expansion": "oum",
"name": "pac-verb"
}
],
"lang": "Pacoh",
"lang_code": "pac",
"pos": "verb",
"senses": [
{
"categories": [
"Pacoh entries with incorrect language header",
"Pacoh lemmas",
"Pacoh terms derived from Proto-Katuic",
"Pacoh terms derived from Proto-Mon-Khmer",
"Pacoh terms inherited from Proto-Katuic",
"Pacoh terms inherited from Proto-Mon-Khmer",
"Pacoh verbs",
"Pages with 2 entries",
"Pages with entries",
"Parauk terms in nonstandard scripts"
],
"glosses": [
"to winnow grains"
],
"links": [
[
"winnow",
"winnow"
],
[
"grain",
"grain"
]
],
"qualifier": "Tal-ay dialect",
"raw_glosses": [
"(Tal-ay dialect) to winnow grains"
]
}
],
"sounds": [
{
"ipa": "[ʔṵːm]"
}
],
"synonyms": [
{
"alt": "Kadô",
"word": "om"
}
],
"word": "oum"
}
Download raw JSONL data for oum meaning in All languages combined (2.5kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2025-01-10 from the enwiktionary dump dated 2025-01-01 using wiktextract (df33d17 and 4ed51a5). 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.