Triple

T17183451
Position Surface form Disambiguated ID Type / Status
Subject Hellbound E417037 entity
Predicate creator P184 FINISHED
Object Yeon Sang-ho E557669 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: Yeon Sang-ho | Statement: [Hellbound, creator, Yeon Sang-ho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yeon Sang-ho
Context triple: [Hellbound, creator, Yeon Sang-ho]
  • A. Yeon Sang-ho chosen
    Yeon Sang-ho is a South Korean filmmaker best known internationally for directing the hit zombie thriller "Train to Busan" and its related works.
  • B. Yoo Soon-taek
    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.
  • C. 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.
  • D. Hwang Jang-lee
    Hwang Jang-lee is a Korean martial artist and actor famed for his villainous kicking roles in classic Hong Kong kung fu films.
  • E. Kim Jee-woon
    Kim Jee-woon is a South Korean film director and screenwriter known for his stylish, genre-spanning works such as "A Tale of Two Sisters," "A Bittersweet Life," and "I Saw the Devil."
  • 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42d9416a48190a5930fcd6008dbaa completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0148490e448190a871483f81394aab completed May 11, 2026, 3:08 a.m.
Created at: April 10, 2026, 5:37 a.m.