Triple

T17074979
Position Surface form Disambiguated ID Type / Status
Subject Police Story 4: First Strike E414324 entity
Predicate starring P1507 FINISHED
Object Bill Tung E1248817 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: Bill Tung | Statement: [Police Story 4: First Strike, starring, Bill Tung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Tung
Context triple: [Police Story 4: First Strike, starring, Bill Tung]
  • A. Bill Tung chosen
    Bill Tung was a popular Hong Kong actor and horse racing commentator best known internationally for his frequent supporting roles alongside Jackie Chan in action-comedy films.
  • B. Stanley Tong
    Stanley Tong is a Hong Kong film director and action choreographer best known for his collaborations with Jackie Chan on high-energy martial arts and action-comedy films.
  • C. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • D. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • E. Cliff Chiang
    Cliff Chiang is an American comic book artist best known for co-creating and illustrating the sci-fi comic series "Paper Girls" and his acclaimed work at DC Comics, including runs on "Wonder Woman."
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbc47808819088a4ca039689b213 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0170df4d1c81909dd05abfd1cfc2ac completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:34 a.m.