Triple

T2140737
Position Surface form Disambiguated ID Type / Status
Subject Afghan American E46753 entity
Predicate ethnicSubgroup P1969 FINISHED
Object Hazara E22784 NE FINISHED

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: Hazara | Statement: [Afghan American, ethnicSubgroup, Hazara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hazara
Context triple: [Afghan American, ethnicSubgroup, Hazara]
  • A. Hazara
    Hazara is a mountainous region in northern Pakistan, known for its diverse ethnic communities, strategic location near the Himalayas, and historical significance under various empires and states.
  • B. Hazaras chosen
    Hazaras are an ethnic group primarily from central Afghanistan, distinguished by their Mongol-influenced ancestry, Shia Muslim majority, and use of Persian (Hazaragi) as their main language.
  • C. Hazaragi
    Hazaragi is a variety of Persian primarily spoken by the Hazara people of central Afghanistan and surrounding regions, distinguished by its unique phonology and significant Turkic and Mongolic influences.
  • D. Hazarajat
    Hazarajat is a mountainous central region of Afghanistan that serves as the traditional homeland of the Hazara people.
  • E. Wakhi
    Wakhi is an Eastern Iranian language traditionally spoken by the Wakhi people in the high mountain regions of Pakistan, Afghanistan, Tajikistan, and China.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88a174ab48190a5db20c132e5dccf completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbe04135c8190ab100b4b3879cb01 completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58d5535c8190b59293afe3a10834 completed March 9, 2026, 5:21 a.m.
Created at: March 4, 2026, 7:44 p.m.