Triple
T22158243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hotien |
E547596
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Uyghur |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Uyghur | Statement: [Hotien, language, Uyghur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uyghur Context triple: [Hotien, language, Uyghur]
-
A.
Uyghur language
chosen
The Uyghur language is a Turkic language spoken primarily by the Uyghur people in China’s Xinjiang region, written in several scripts and serving as a major language of Central Asia.
-
B.
Uyghurs
The Uyghurs are a Turkic-speaking, predominantly Muslim ethnic group native to the Xinjiang region of northwest China, with a distinct culture, language, and history.
-
C.
Uyghur Arabic alphabet
The Uyghur Arabic alphabet is a Perso-Arabic–based script adapted to represent the sounds of the Uyghur language, historically used by Uyghur communities in Central Asia.
-
D.
Uyghur Cyrillic alphabet
The Uyghur Cyrillic alphabet is a Cyrillic-based script historically used by Uyghur communities, particularly in the former Soviet Union, to write the Uyghur language.
-
E.
Uyghur Latin alphabet
The Uyghur Latin alphabet is a romanized writing system developed for the Uyghur language, used primarily in digital communication and linguistic transcription.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12a2aadb48190b4d739d1df9529db |
completed | April 28, 2026, 9:44 p.m. |
Created at: April 16, 2026, 8:33 p.m.