JSON data structure browser

Download full JSON mapping

Fields and tags index

The raw JSON data used to generate this site consists of individual JSON object for each separate word. The browser here is a union of all these objects combined into one, by recursively delving through each of them and adding newly found nodes in a parallel mapping.

{
"anagrams":
[
{
"word": word seen in May [Bahasa Inggeris]; reached 144 times
}
]
"antonyms":
[
{
"sense": sense seen in damaging [Bahasa Inggeris]; reached 392 times,
"word": word seen in damaging [Bahasa Inggeris]; reached 858 times
}
]
"categories":
[categories seen in Czech Republic [Bahasa Inggeris]; reached 384200 times]
"classifiers":
[
{
"classifier": classifier seen in เต่า [Bahasa Thai]; reached 45 times,
"raw_tags":
[raw_tags seen in เต่า [Bahasa Thai]; reached 44 times]
}
]
"coordinate_terms":
[
{
"sense": sense seen in no longer [Bahasa Inggeris]; reached 105 times,
"word": word seen in no longer [Bahasa Inggeris]; reached 105 times
}
]
"derived":
[
{
"sense": sense seen in adjutant [Bahasa Inggeris]; reached 219 times,
"word": word seen in latent [Bahasa Inggeris]; reached 19046 times
}
]
"etymology_texts":
[etymology_texts seen in Czech Republic [Bahasa Inggeris]; reached 16796 times]
"forms":
[
{
"form": form seen in spa [Bahasa Inggeris]; reached 28416 times,
"raw_tags":
[raw_tags seen in spa [Bahasa Inggeris]; reached 11172 times]
"tags":
[tags seen in septillion [Bahasa Inggeris]; reached 17240 times]
}
]
"hypernyms":
[
{
"sense": sense seen in all in [Bahasa Inggeris]; reached 5 times,
"word": word seen in all in [Bahasa Inggeris]; reached 5 times
}
]
"hyphenations":
[
{
"parts":
[parts seen in magnetism [Bahasa Inggeris]; reached 34901 times]
}
]
"hyponyms":
[
{
"sense": sense seen in computer [Bahasa Inggeris]; reached 15 times,
"word": word seen in computer [Bahasa Inggeris]; reached 15 times
}
]
"lang": lang seen in Czech Republic [Bahasa Inggeris]; reached 74150 times,
"lang_code": lang_code seen in Czech Republic [Bahasa Inggeris]; reached 74150 times,
"notes":
[notes seen in GOAT [Bahasa Inggeris]; reached 253 times]
"pos": pos seen in Czech Republic [Bahasa Inggeris]; reached 74150 times,
"pos_title": pos_title seen in Czech Republic [Bahasa Inggeris]; reached 70162 times,
"proverbs":
[
{
"sense": sense seen in bahasa [Bahasa Melayu]; reached 21 times,
"word": word seen in the early bird catches the worm [Bahasa Inggeris]; reached 68 times
}
]
"related":
[
{
"sense": sense seen in ゔ [Bahasa Jepun]; reached 3 times,
"word": word seen in zygote [Bahasa Inggeris]; reached 281 times
}
]
"senses":
[
{
"alt_of":
[
{
"word": word seen in goat [Bahasa Inggeris]; reached 5 times
}
]
"attestations":
[
{
"date": date seen in computer [Bahasa Inggeris]; reached 23 times
}
]
"categories":
[categories seen in spa [Bahasa Inggeris]; reached 27016 times]
"examples":
[
{
"bold_literal_offsets":
[
[bold_literal_offsets seen in nanam [Bahasa Suluk]; reached 6 times]
]
"bold_roman_offsets":
[
[bold_roman_offsets seen in bertemper [Bahasa Melayu]; reached 138 times]
]
"bold_text_offsets":
[
[bold_text_offsets seen in no longer [Bahasa Inggeris]; reached 34092 times]
]
"bold_translation_offsets":
[
[bold_translation_offsets seen in no longer [Bahasa Inggeris]; reached 32838 times]
]
"literal_meaning": literal_meaning seen in nanam [Bahasa Suluk]; reached 5 times,
"ref": ref seen in leave someone out in the cold [Bahasa Inggeris]; reached 291 times,
"roman": roman seen in bertemper [Bahasa Melayu]; reached 108 times,
"text": text seen in no longer [Bahasa Inggeris]; reached 19285 times,
"translation": translation seen in no longer [Bahasa Inggeris]; reached 18490 times
}
]
"form_of":
[
{
"word": word seen in calme [Bahasa Inggeris]; reached 1879 times
}
]
"glosses":
[glosses seen in Czech Republic [Bahasa Inggeris]; reached 82157 times]
"raw_tags":
[raw_tags seen in spa [Bahasa Inggeris]; reached 3177 times]
"tags":
[tags seen in lanjiao [Bahasa Inggeris]; reached 7442 times]
"topics":
[topics seen in magnetism [Bahasa Inggeris]; reached 3582 times]
}
]
"sounds":
[
{
"audio": audio seen in Czech Republic [Bahasa Inggeris]; reached 4154 times,
"flac_url": flac_url seen in siku kuu [Bahasa Swahili]; reached 7 times,
"hangeul": hangeul seen in 종목 [Bahasa Korea]; reached 143 times,
"ipa": ipa seen in Czech Republic [Bahasa Inggeris]; reached 15167 times,
"mp3_url": mp3_url seen in Czech Republic [Bahasa Inggeris]; reached 4154 times,
"oga_url": oga_url seen in spa [Bahasa Inggeris]; reached 41 times,
"ogg_url": ogg_url seen in Czech Republic [Bahasa Inggeris]; reached 4114 times,
"opus_url": opus_url seen in methyl [Bahasa Inggeris]; reached 4 times,
"other": other seen in Google [Bahasa Inggeris]; reached 7130 times,
"raw_tags":
[raw_tags seen in Czech Republic [Bahasa Inggeris]; reached 8439 times]
"rhymes": rhymes seen in Czech Republic [Bahasa Inggeris]; reached 8293 times,
"roman": roman seen in 종목 [Bahasa Korea]; reached 505 times,
"tags":
[tags seen in spa [Bahasa Inggeris]; reached 2498 times]
"wav_url": wav_url seen in magnetism [Bahasa Inggeris]; reached 1140 times
}
]
"synonyms":
[
{
"sense": sense seen in heavy metal [Bahasa Inggeris]; reached 2834 times,
"word": word seen in heavy metal [Bahasa Inggeris]; reached 5319 times
}
]
"tags":
[tags seen in inter- [Bahasa Inggeris]; reached 2474 times]
"translations":
[
{
"lang": lang seen in normothermic [Bahasa Inggeris]; reached 34890 times,
"lang_code": lang_code seen in normothermic [Bahasa Inggeris]; reached 34890 times,
"raw_tags":
[raw_tags seen in Wiktionary [Bahasa Inggeris]; reached 1395 times]
"roman": roman seen in normothermic [Bahasa Inggeris]; reached 11292 times,
"sense": sense seen in normothermic [Bahasa Inggeris]; reached 34712 times,
"source": source seen in Rōmaji [Bahasa Inggeris]; reached 385 times,
"tags":
[tags seen in mahout [Bahasa Inggeris]; reached 13759 times]
"word": word seen in normothermic [Bahasa Inggeris]; reached 34890 times
}
]
"word": word seen in Czech Republic [Bahasa Inggeris]; reached 74150 times
}

This page is a part of the kaikki.org machine-readable dictionary. This dictionary is based on structured data extracted on 2026-01-25 from the mswiktionary dump dated 2026-01-01 using wiktextract (f492ef9 and 9905b1f). 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.