Triple

T22396298
Position Surface form Disambiguated ID Type / Status
Subject Junggumun E553638 entity
Predicate relatedTo P37 FINISHED
Object Hyangchal 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: Hyangchal | Statement: [Junggumun, relatedTo, Hyangchal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hyangchal
Context triple: [Junggumun, relatedTo, Hyangchal]
  • A. Hyangchal chosen
    Hyangchal is an ancient Korean writing system that used Chinese characters phonetically and semantically to transcribe native Korean, especially in early vernacular poetry.
  • B. Hyangak
    Hyangak is a traditional Korean court and folk music style that developed indigenously on the Korean peninsula, distinct from imported musical forms.
  • C. Hwangje
    Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
  • D. Donhwamun
    Donhwamun is the main gate of Changdeokgung Palace in Seoul, South Korea, and one of the oldest surviving palace gates from the Joseon Dynasty.
  • E. Yeongdodaegyo
    Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1585e84b081908c95ed3e0d987ed8 completed April 29, 2026, 1:01 a.m.
Created at: April 16, 2026, 8:45 p.m.