Triple

T4588214
Position Surface form Disambiguated ID Type / Status
Subject Kunsan Air Base E103419 entity
Predicate near P350 FINISHED
Object Gunsan city E478252 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: Gunsan city | Statement: [Kunsan Air Base, near, Gunsan city]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gunsan city
Context triple: [Kunsan Air Base, near, Gunsan city]
  • A. Gunsan chosen
    Gunsan is a coastal city in North Jeolla Province, South Korea, known for its port, industrial facilities, and longstanding association with nearby military air operations.
  • B. Chuncheon
    Chuncheon is a city in northeastern South Korea known for its lakes, surrounding mountains, and status as the capital of Gangwon Province.
  • C. Icheon
    Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
  • D. Yeoju
    Yeoju is a city in South Korea known for its rich historical heritage, including royal tombs and ceramics, and its scenic riverside landscapes.
  • E. Cheongju
    Cheongju is a major city in central South Korea that serves as the capital of North Chungcheong Province and an important regional administrative, educational, and transportation hub.
  • 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_69bd43dccaf08190aa89e9991a289719 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd592115fc8190b1aee1d8bbaf1ee3 completed March 20, 2026, 2:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69be777f287c81909f700e22163ccc24 completed March 21, 2026, 10:48 a.m.
Created at: March 20, 2026, 1:11 p.m.