Triple

T10847720
Position Surface form Disambiguated ID Type / Status
Subject Ban Hyun-hee E256057 entity
Predicate parent P120 FINISHED
Object Yoo Soon-taek E51441 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: Yoo Soon-taek | Statement: [Ban Hyun-hee, parent, Yoo Soon-taek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yoo Soon-taek
Context triple: [Ban Hyun-hee, parent, Yoo Soon-taek]
  • A. Yoo Soon-taek chosen
    Yoo Soon-taek is a South Korean figure best known as the wife of former United Nations Secretary-General Ban Ki-moon and for her involvement in various social and charitable activities.
  • B. Kim Ki-young
    Kim Ki-young was a pioneering South Korean film director best known for his psychologically intense, genre-blending works such as "The Housemaid," which deeply influenced later auteurs like Bong Joon-ho.
  • C. Yeon Sang-ho
    Yeon Sang-ho is a South Korean filmmaker best known internationally for directing the hit zombie thriller "Train to Busan" and its related works.
  • D. Im Kwon-taek
    Im Kwon-taek is a pioneering South Korean film director renowned for his prolific career and influential works that helped shape modern Korean cinema.
  • E. Na Hong-jin
    Na Hong-jin is a South Korean filmmaker renowned for his intense, genre-blending thrillers such as "The Chaser," "The Yellow Sea," and "The Wailing."
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75113bc188190ac78df0c51d95de6 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb170e714819097babb2b850342d2 completed April 14, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:20 p.m.