Triple

T19116450
Position Surface form Disambiguated ID Type / Status
Subject Mayor of Seoul E467918 entity
Predicate hasHadOfficeHolder P9949 FINISHED
Object Goh Kun 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: Goh Kun | Statement: [Mayor of Seoul, hasHadOfficeHolder, Goh Kun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Goh Kun
Context triple: [Mayor of Seoul, hasHadOfficeHolder, Goh Kun]
  • A. Goh Kun chosen
    Goh Kun is a South Korean politician and bureaucrat who served as Prime Minister and held multiple key administrative posts, including leadership roles in Seoul's municipal government.
  • B. Maki Goto
    Maki Goto is a Japanese pop singer, actress, and former member of the idol group Morning Musume who gained prominence in the early 2000s.
  • C. Shinpei
    Shinpei is a Japanese given name commonly used for males and borne by various notable figures in politics, arts, and entertainment.
  • D. Go Shiina
    Go Shiina is a Japanese composer known for his dramatic, richly orchestrated soundtracks for anime, video games, and television.
  • E. Hajino Nakatomo
    Hajino Nakatomo is a revered figure in Japanese Shinto tradition who is venerated as one of the deities associated with the famous Sanja Matsuri festival in Tokyo.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3984bf48190818fa2b01b75decb completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:05 p.m.