Triple

T17024482
Position Surface form Disambiguated ID Type / Status
Subject Police Story 3: Supercop E413027 entity
Predicate screenwriter P2831 FINISHED
Object Fong Chi-keung E1257965 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: Fong Chi-keung | Statement: [Police Story 3: Supercop, screenwriter, Fong Chi-keung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fong Chi-keung
Context triple: [Police Story 3: Supercop, screenwriter, Fong Chi-keung]
  • A. Fong Chi-keung chosen
    Fong Chi-keung is a Hong Kong screenwriter best known for his work on action films, including the Jackie Chan hit "Rumble in the Bronx."
  • B. Chow Shiu-hung
    Chow Shiu-hung is an individual notable for bearing the Chinese surname Chow, recognized in records of people with this family name.
  • C. Yuen Siu-tien
    Yuen Siu-tien was a Hong Kong martial arts film actor best known for his iconic portrayal of the drunken master Beggar So in classic kung fu cinema.
  • D. Yam Kim-fai
    Yam Kim-fai was a legendary Cantonese opera star renowned for her charismatic male "sheng" roles and lasting influence on Hong Kong’s performing arts.
  • E. Lok Fu
    Lok Fu is a residential neighborhood and transport hub in Hong Kong known for its public housing estates, shopping centre, and MTR station.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d371148190a60d32a72abec09a completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0170df4d1c81909dd05abfd1cfc2ac completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:33 a.m.