Triple

T20748145
Position Surface form Disambiguated ID Type / Status
Subject Jinju-si E510642 entity
Predicate nearCity P350 FINISHED
Object Haman-gun 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: Haman-gun | Statement: [Jinju-si, nearCity, Haman-gun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haman-gun
Context triple: [Jinju-si, nearCity, Haman-gun]
  • A. Haman-gun chosen
    Haman-gun is a rural county in South Gyeongsang Province, South Korea, known for its agricultural landscape and historical sites.
  • B. Haeju
    Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
  • C. Musan
    Musan is a mining town in northeastern North Korea known for its large iron ore deposits and proximity to the Chinese border.
  • D. Hajong
    The Hajong are an indigenous ethnic group of northeastern India and neighboring Bangladesh, known for their Tibeto-Burman origins, agrarian lifestyle, and distinct language and cultural traditions.
  • E. Komam-ni
    Komam-ni is a village in South Korea known for being a key site of fighting during the Korean War’s Battle of Masan.
  • 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_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c226fbf881909794eff3ee9e206b completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:33 p.m.