Triple

T22169833
Position Surface form Disambiguated ID Type / Status
Subject Xinjiang Wars E547888 entity
Predicate involvesEthnicGroup P194 FINISHED
Object Kyrgyz 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: Kyrgyz | Statement: [Xinjiang Wars, involvesEthnicGroup, Kyrgyz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kyrgyz
Context triple: [Xinjiang Wars, involvesEthnicGroup, Kyrgyz]
  • A. Kyrgyz
    Kyrgyz is a Turkic language primarily spoken in Kyrgyzstan and surrounding regions of Central Asia.
  • B. Kyrgyz people chosen
    The Kyrgyz people are a Turkic ethnic group native to Central Asia, primarily inhabiting Kyrgyzstan, with a rich nomadic heritage and traditions centered around horsemanship, yurt-dwelling, and epic oral literature.
  • C. Qaramqol
    Qaramqol is a town and district center in northern Afghanistan, located within Faryab Province.
  • D. Kyrgyzstan
    Kyrgyzstan is a landlocked Central Asian country known for its mountainous terrain, nomadic heritage, and status as a former Soviet republic.
  • E. Qarluq
    Qarluq refers to a historical Turkic tribal confederation that played a key role in Central Asian politics and the formation of early Turkic states.
  • 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_69e11e3c4c5c81908d336165816b12e0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a67f4dc81909cc5f8d2c1fe6129 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.