See ສົ້ມ in All languages combined, or Wiktionary
{
"etymology_templates": [
{
"args": {
"1": "lo",
"2": "tai-pro",
"3": "*sɤmᶜ",
"4": "",
"5": "sour"
},
"expansion": "Proto-Tai *sɤmᶜ (“sour”)",
"name": "inh"
},
{
"args": {
"1": "th",
"2": "ส้ม"
},
"expansion": "Thai ส้ม (sôm)",
"name": "cog"
},
{
"args": {
"1": "khb",
"2": "ᦉᦳᧄᧉ"
},
"expansion": "Lü ᦉᦳᧄᧉ (ṡum²)",
"name": "cog"
},
{
"args": {
"1": "blt",
"2": "ꪶꪎ꫁ꪣ"
},
"expansion": "Tai Dam ꪶꪎ꫁ꪣ",
"name": "cog"
},
{
"args": {
"1": "shn",
"2": "သူမ်ႈ"
},
"expansion": "Shan သူမ်ႈ (sūum)",
"name": "cog"
},
{
"args": {
"1": "aho",
"2": "𑜏𑜤𑜪"
},
"expansion": "Ahom 𑜏𑜤𑜪 (suṃ)",
"name": "cog"
},
{
"args": {
"1": "za",
"2": "soemj"
},
"expansion": "Zhuang soemj",
"name": "cog"
},
{
"args": {
"1": "ltc",
"2": "-"
},
"expansion": "Middle Chinese",
"name": "cog"
},
{
"args": {
"1": "酸",
"2": "sour"
},
"expansion": "酸 (MC swan, “sour”)",
"name": "ltc-l"
},
{
"args": {
"1": "poz-pro",
"2": "*qaləsəm"
},
"expansion": "Proto-Malayo-Polynesian *qaləsəm",
"name": "cog"
},
{
"args": {
"1": "ms",
"2": "asam"
},
"expansion": "Malay asam",
"name": "cog"
},
{
"args": {
"1": "bbc",
"2": "asom"
},
"expansion": "Toba Batak asom",
"name": "cog"
}
],
"etymology_text": "From Proto-Tai *sɤmᶜ (“sour”). Cognate with Thai ส้ม (sôm), Lü ᦉᦳᧄᧉ (ṡum²), Tai Dam ꪶꪎ꫁ꪣ, Shan သူမ်ႈ (sūum), Ahom 𑜏𑜤𑜪 (suṃ), Zhuang soemj. Compare Middle Chinese 酸 (MC swan, “sour”) and Proto-Malayo-Polynesian *qaləsəm (whence Malay asam and Toba Batak asom).",
"forms": [
{
"form": "som",
"tags": [
"romanization"
]
},
{
"form": "ຄວາມສົ້ມ",
"tags": [
"abstract-noun"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "ສົ້ມ • (som) (abstract noun ຄວາມສົ້ມ)",
"name": "lo-adj"
}
],
"hyphenation": [
"ສົ້ມ"
],
"lang": "Lao",
"lang_code": "lo",
"pos": "adj",
"related": [
{
"_dis1": "0 0",
"roman": "wān",
"word": "ຫວານ"
},
{
"_dis1": "0 0",
"roman": "piāu",
"word": "ປ້ຽວ"
},
{
"_dis1": "0 0",
"roman": "khem",
"word": "ເຄັມ"
},
{
"_dis1": "0 0",
"roman": "khom",
"word": "ຂົມ"
},
{
"_dis1": "0 0",
"roman": "phet",
"word": "ເຜັດ"
},
{
"_dis1": "0 0",
"roman": "ʼū mā mī",
"word": "ອູມາມີ"
},
{
"_dis1": "0 0",
"roman": "khāo",
"word": "ຂາວ"
},
{
"_dis1": "0 0",
"roman": "thao",
"word": "ເທົາ"
},
{
"_dis1": "0 0",
"roman": "ngœn",
"word": "ເງິນ"
},
{
"_dis1": "0 0",
"english": "dam",
"word": "ດຳ"
},
{
"_dis1": "0 0",
"roman": "dǣng",
"word": "ແດງ"
},
{
"_dis1": "0 0",
"roman": "dǣngkhem",
"word": "ແດງເຂັ້ມ"
},
{
"_dis1": "0 0",
"roman": "nam tān",
"word": "ນ້ຳຕານ"
},
{
"_dis1": "0 0",
"roman": "lư̄ang",
"word": "ເຫຼືອງ"
},
{
"_dis1": "0 0",
"roman": "khīm",
"word": "ຄີມ"
},
{
"_dis1": "0 0",
"roman": "māk nāokhiāu",
"word": "ໝາກນາວຂຽວ"
},
{
"_dis1": "0 0",
"roman": "khiāu",
"word": "ຂຽວ"
},
{
"_dis1": "0 0",
"roman": "khiāuʼǭn",
"word": "ຂຽວອ່ອນ"
},
{
"_dis1": "0 0",
"roman": "khiāukhem",
"word": "ຂຽວເຂັ້ມ"
},
{
"_dis1": "0 0",
"roman": "fākhiāu",
"word": "ຟ້າຂຽວ"
},
{
"_dis1": "0 0",
"roman": "fākhiāukhem",
"word": "ຟ້າຂຽວເຂັ້ມ"
},
{
"_dis1": "0 0",
"roman": "thǭng fā",
"word": "ທ້ອງຟ້າ"
},
{
"_dis1": "0 0",
"roman": "fā",
"word": "ຟ້າ"
},
{
"_dis1": "0 0",
"roman": "mūangʼǭn",
"word": "ມ່ວງອ່ອນ"
},
{
"_dis1": "0 0",
"roman": "fāmūangkhem",
"word": "ຟ້າມ່ວງເຂັ້ມ"
},
{
"_dis1": "0 0",
"roman": "mūangdǣng",
"word": "ມ່ວງແດງ"
},
{
"_dis1": "0 0",
"roman": "mūang",
"word": "ມ່ວງ"
},
{
"_dis1": "0 0",
"roman": "būa",
"word": "ບົວ"
}
],
"senses": [
{
"categories": [
{
"_dis": "50 50",
"kind": "other",
"name": "Lao entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "50 50",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "50 50",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"sour"
],
"id": "en-ສົ້ມ-lo-adj-DUJoWR14",
"links": [
[
"sour",
"sour"
]
]
},
{
"categories": [
{
"_dis": "50 50",
"kind": "other",
"name": "Lao entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "50 50",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "50 50",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"orange"
],
"id": "en-ສົ້ມ-lo-adj-G0yRM9pz",
"links": [
[
"orange",
"orange"
]
]
}
],
"sounds": [
{
"ipa": "[som˧˩]",
"note": "Vientiane"
},
{
"ipa": "[som˥˥˨]",
"note": "Luang Prabang"
},
{
"rhymes": "-om"
}
],
"word": "ສົ້ມ"
}
{
"categories": [
"Lao 1-syllable words",
"Lao adjectives",
"Lao entries with incorrect language header",
"Lao lemmas",
"Lao terms derived from Proto-Tai",
"Lao terms inherited from Proto-Tai",
"Lao terms with IPA pronunciation",
"Pages with 1 entry",
"Pages with entries",
"Rhymes:Lao/om"
],
"etymology_templates": [
{
"args": {
"1": "lo",
"2": "tai-pro",
"3": "*sɤmᶜ",
"4": "",
"5": "sour"
},
"expansion": "Proto-Tai *sɤmᶜ (“sour”)",
"name": "inh"
},
{
"args": {
"1": "th",
"2": "ส้ม"
},
"expansion": "Thai ส้ม (sôm)",
"name": "cog"
},
{
"args": {
"1": "khb",
"2": "ᦉᦳᧄᧉ"
},
"expansion": "Lü ᦉᦳᧄᧉ (ṡum²)",
"name": "cog"
},
{
"args": {
"1": "blt",
"2": "ꪶꪎ꫁ꪣ"
},
"expansion": "Tai Dam ꪶꪎ꫁ꪣ",
"name": "cog"
},
{
"args": {
"1": "shn",
"2": "သူမ်ႈ"
},
"expansion": "Shan သူမ်ႈ (sūum)",
"name": "cog"
},
{
"args": {
"1": "aho",
"2": "𑜏𑜤𑜪"
},
"expansion": "Ahom 𑜏𑜤𑜪 (suṃ)",
"name": "cog"
},
{
"args": {
"1": "za",
"2": "soemj"
},
"expansion": "Zhuang soemj",
"name": "cog"
},
{
"args": {
"1": "ltc",
"2": "-"
},
"expansion": "Middle Chinese",
"name": "cog"
},
{
"args": {
"1": "酸",
"2": "sour"
},
"expansion": "酸 (MC swan, “sour”)",
"name": "ltc-l"
},
{
"args": {
"1": "poz-pro",
"2": "*qaləsəm"
},
"expansion": "Proto-Malayo-Polynesian *qaləsəm",
"name": "cog"
},
{
"args": {
"1": "ms",
"2": "asam"
},
"expansion": "Malay asam",
"name": "cog"
},
{
"args": {
"1": "bbc",
"2": "asom"
},
"expansion": "Toba Batak asom",
"name": "cog"
}
],
"etymology_text": "From Proto-Tai *sɤmᶜ (“sour”). Cognate with Thai ส้ม (sôm), Lü ᦉᦳᧄᧉ (ṡum²), Tai Dam ꪶꪎ꫁ꪣ, Shan သူမ်ႈ (sūum), Ahom 𑜏𑜤𑜪 (suṃ), Zhuang soemj. Compare Middle Chinese 酸 (MC swan, “sour”) and Proto-Malayo-Polynesian *qaləsəm (whence Malay asam and Toba Batak asom).",
"forms": [
{
"form": "som",
"tags": [
"romanization"
]
},
{
"form": "ຄວາມສົ້ມ",
"tags": [
"abstract-noun"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "ສົ້ມ • (som) (abstract noun ຄວາມສົ້ມ)",
"name": "lo-adj"
}
],
"hyphenation": [
"ສົ້ມ"
],
"lang": "Lao",
"lang_code": "lo",
"pos": "adj",
"related": [
{
"roman": "wān",
"word": "ຫວານ"
},
{
"roman": "piāu",
"word": "ປ້ຽວ"
},
{
"roman": "khem",
"word": "ເຄັມ"
},
{
"roman": "khom",
"word": "ຂົມ"
},
{
"roman": "phet",
"word": "ເຜັດ"
},
{
"roman": "ʼū mā mī",
"word": "ອູມາມີ"
},
{
"roman": "khāo",
"word": "ຂາວ"
},
{
"roman": "thao",
"word": "ເທົາ"
},
{
"roman": "ngœn",
"word": "ເງິນ"
},
{
"english": "dam",
"word": "ດຳ"
},
{
"roman": "dǣng",
"word": "ແດງ"
},
{
"roman": "dǣngkhem",
"word": "ແດງເຂັ້ມ"
},
{
"roman": "nam tān",
"word": "ນ້ຳຕານ"
},
{
"roman": "lư̄ang",
"word": "ເຫຼືອງ"
},
{
"roman": "khīm",
"word": "ຄີມ"
},
{
"roman": "māk nāokhiāu",
"word": "ໝາກນາວຂຽວ"
},
{
"roman": "khiāu",
"word": "ຂຽວ"
},
{
"roman": "khiāuʼǭn",
"word": "ຂຽວອ່ອນ"
},
{
"roman": "khiāukhem",
"word": "ຂຽວເຂັ້ມ"
},
{
"roman": "fākhiāu",
"word": "ຟ້າຂຽວ"
},
{
"roman": "fākhiāukhem",
"word": "ຟ້າຂຽວເຂັ້ມ"
},
{
"roman": "thǭng fā",
"word": "ທ້ອງຟ້າ"
},
{
"roman": "fā",
"word": "ຟ້າ"
},
{
"roman": "mūangʼǭn",
"word": "ມ່ວງອ່ອນ"
},
{
"roman": "fāmūangkhem",
"word": "ຟ້າມ່ວງເຂັ້ມ"
},
{
"roman": "mūangdǣng",
"word": "ມ່ວງແດງ"
},
{
"roman": "mūang",
"word": "ມ່ວງ"
},
{
"roman": "būa",
"word": "ບົວ"
}
],
"senses": [
{
"glosses": [
"sour"
],
"links": [
[
"sour",
"sour"
]
]
},
{
"glosses": [
"orange"
],
"links": [
[
"orange",
"orange"
]
]
}
],
"sounds": [
{
"ipa": "[som˧˩]",
"note": "Vientiane"
},
{
"ipa": "[som˥˥˨]",
"note": "Luang Prabang"
},
{
"rhymes": "-om"
}
],
"word": "ສົ້ມ"
}
Download raw JSONL data for ສົ້ມ meaning in Lao (3.8kB)
This page is a part of the kaikki.org machine-readable Lao 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.