Triple

T23404923
Position Surface form Disambiguated ID Type / Status
Subject Kaepung County E559608 entity
Predicate romanization P2508 FINISHED
Object Kaepung-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: Kaepung-gun | Statement: [Kaepung County, romanization, Kaepung-gun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaepung-gun
Context triple: [Kaepung County, romanization, Kaepung-gun]
  • A. Taebong
    Taebong was a short-lived Korean kingdom of the early 10th century that emerged during the Later Three Kingdoms period before being absorbed by Goryeo.
  • B. Songak-gun
    Songak-gun was a historical county in Korea that served as the capital of the short-lived Later Three Kingdoms state of Taebong in the early 10th century.
  • C. Kaepung-ŭp chosen
    Kaepung-ŭp is the principal town and administrative center of Kaepung County in North Korea.
  • D. Hadong-gun
    Hadong-gun is a rural county in South Gyeongsang Province, South Korea, known for its scenic Seomjin River landscapes, green tea fields, and traditional cultural heritage.
  • E. Yeongneung
    Yeongneung is a royal tomb complex in Yeoju, South Korea, that houses the burial site of King Sejong the Great and is part of the UNESCO-listed Royal Tombs of the Joseon Dynasty.
  • 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_69e24549610c8190a069d6411ce5f661 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a4e27db88190b37375b38073291c completed April 29, 2026, 6:27 a.m.
Created at: April 17, 2026, 5:38 p.m.