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.

{
"antonyms":
[
{
"raw_tags":
[raw_tags seen in nasákavý [čeština]; reached 221 times]
"sense_index": sense_index seen in datovka [čeština]; reached 21187 times,
"tags":
[tags seen in zamračeno [čeština]; reached 286 times]
"word": word seen in datovka [čeština]; reached 21545 times
}
]
"categories":
[categories seen in postava [čeština]; reached 316973 times]
"derived":
[
{
"word": word seen in 有る [japonština]; reached 205 times
}
]
"etymology_texts":
[etymology_texts seen in dvouletý [čeština]; reached 31585 times]
"forms":
[
{
"form": form seen in postava [čeština]; reached 1610763 times,
"raw_tags":
[raw_tags seen in koleno [čeština]; reached 431192 times]
"roman": roman seen in 会う [japonština]; reached 411 times,
"tags":
[tags seen in postava [čeština]; reached 4896893 times]
}
]
"hyphenations":
[
{
"parts":
[parts seen in postava [čeština]; reached 218194 times]
}
]
"lang": lang seen in postava [čeština]; reached 191075 times,
"lang_code": lang_code seen in postava [čeština]; reached 191075 times,
"note": note seen in kolehiyo [tagalog]; reached 21 times,
"phrases":
[
{
"word": word seen in píše [čeština]; reached 10 times
}
]
"pos": pos seen in postava [čeština]; reached 191075 times,
"pos_title": pos_title seen in postava [čeština]; reached 191075 times,
"proverbs":
[
{
"sense_index": sense_index seen in šplouchat [čeština]; reached 4 times,
"word": word seen in jazyk [čeština]; reached 1566 times
}
]
"raw_tags":
[raw_tags seen in hnusit se [čeština]; reached 62507 times]
"related":
[
{
"raw_tags":
[raw_tags seen in huba [čeština]; reached 12 times]
"sense_index": sense_index seen in rikších [čeština]; reached 781 times,
"tags":
[tags seen in sport [čeština]; reached 41 times]
"word": word seen in postava [čeština]; reached 264617 times
}
]
"senses":
[
{
"categories":
[categories seen in duktilní [čeština]; reached 32234 times]
"examples":
[
{
"bold_text_offsets":
[
[bold_text_offsets seen in Uzbek [čeština]; reached 45030 times]
]
"ref": ref seen in dvouletý [čeština]; reached 31202 times,
"text": text seen in postava [čeština]; reached 56148 times,
"translation": translation seen in majlant [čeština]; reached 10899 times
}
]
"form_of":
[
{
"word": word seen in ochrance [čeština]; reached 92592 times
}
]
"glosses":
[glosses seen in postava [čeština]; reached 285441 times]
"raw_tags":
[raw_tags seen in třídění [čeština]; reached 8694 times]
"tags":
[tags seen in ochrance [čeština]; reached 114021 times]
"topics":
[topics seen in gen [čeština]; reached 14619 times]
}
]
"sounds":
[
{
"audio": audio seen in koleno [čeština]; reached 40157 times,
"flac_url": flac_url seen in rain fire and brimstone [angličtina]; reached 13 times,
"homophone": homophone seen in voz [čeština]; reached 27001 times,
"ipa": ipa seen in postava [čeština]; reached 163087 times,
"mp3_url": mp3_url seen in koleno [čeština]; reached 40157 times,
"oga_url": oga_url seen in Karviná [čeština]; reached 225 times,
"ogg_url": ogg_url seen in koleno [čeština]; reached 39933 times,
"opus_url": opus_url seen in Athens [angličtina]; reached 5 times,
"other": other seen in внимательный [ruština]; reached 887 times,
"raw_tags":
[raw_tags seen in místnost [čeština]; reached 5084 times]
"tags":
[tags seen in sežrat [čeština]; reached 889 times]
"wav_url": wav_url seen in denně [čeština]; reached 3167 times,
"zh_pron": zh_pron seen in 禍 [čínština]; reached 635 times
}
]
"synonyms":
[
{
"raw_tags":
[raw_tags seen in mrtvolou [čeština]; reached 4258 times]
"sense_index": sense_index seen in hnusit se [čeština]; reached 105976 times,
"tags":
[tags seen in malaga [čeština]; reached 9601 times]
"word": word seen in hnusit se [čeština]; reached 107772 times
}
]
"tags":
[tags seen in postava [čeština]; reached 131847 times]
"translations":
[
{
"lang": lang seen in postava [čeština]; reached 232830 times,
"lang_code": lang_code seen in postava [čeština]; reached 232830 times,
"raw_tags":
[raw_tags seen in nacista [čeština]; reached 1281 times]
"sense": sense seen in dvouletý [čeština]; reached 205090 times,
"sense_index": sense_index seen in postava [čeština]; reached 232830 times,
"tags":
[tags seen in postava [čeština]; reached 92789 times]
"word": word seen in postava [čeština]; reached 232830 times
}
]
"word": word seen in postava [čeština]; reached 191075 times
}

This page is a part of the kaikki.org machine-readable dictionary. This dictionary is based on structured data extracted on 2026-03-25 from the cswiktionary dump dated 2026-03-01 using wiktextract (05c257f and 9d9a410). 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.