Triple

T17038038
Position Surface form Disambiguated ID Type / Status
Subject Pyeongchang E413371 entity
Predicate hasKoreanName P17869 FINISHED
Object 평창군 E561376 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: 평창군 | Statement: [Pyeongchang, hasKoreanName, 평창군]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 평창군
Context triple: [Pyeongchang, hasKoreanName, 평창군]
  • A. Pyeongchang County chosen
    Pyeongchang County is a mountainous region in South Korea best known internationally for hosting the 2018 Winter Olympics.
  • B. Changnyeong County
    Changnyeong County is a rural administrative region in South Gyeongsang Province, South Korea, known for its agricultural landscape and historical sites.
  • C. Jeungpyeong-gun
    Jeungpyeong-gun is a rural county in central South Korea known for its agricultural landscape and location within North Chungcheong Province.
  • D. Yeongyang County
    Yeongyang County is a rural administrative region in eastern South Korea known for its mountainous terrain, low population density, and production of specialty agricultural products such as apples and chili peppers.
  • E. Seocheon County
    Seocheon County is a coastal administrative region in South Chungcheong Province, South Korea, known for its tidal flats, fishing industry, and ecological wetlands.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f45f84819092cfb27cc33da026 completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b5b71f48190b6c865d57668b5d1 completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.