Triple

T17748488
Position Surface form Disambiguated ID Type / Status
Subject Clarence Fok E443046 entity
Predicate directed P7373 FINISHED
Object Her Fatal Ways III 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: Her Fatal Ways III | Statement: [Clarence Fok, directed, Her Fatal Ways III]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Her Fatal Ways III
Context triple: [Clarence Fok, directed, Her Fatal Ways III]
  • A. Her Fatal Ways chosen
    Her Fatal Ways is a Hong Kong action-comedy film best known for its blend of crime, satire, and cross-border cultural clashes.
  • B. Killer Women
    Killer Women is an American crime drama television series that follows a tough female Texas Ranger as she investigates cases involving women accused of murder.
  • C. Deadlier Than the Male
    Deadlier Than the Male is a 1967 British spy thriller film featuring suave insurance investigator Bulldog Drummond battling a pair of glamorous female assassins.
  • D. Deadly Cross
    Deadly Cross is a crime thriller novel in James Patterson’s long-running Alex Cross series, following the detective as he investigates a high-profile double murder in Washington, D.C.
  • E. Hard to Kill
    Hard to Kill is a 1990 action film starring Steven Seagal as a detective who awakens from a coma to seek revenge against corrupt politicians and criminals who tried to kill him.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47ad46a50819089c87f74efe3c7ca completed April 19, 2026, 6:48 a.m.
Created at: April 10, 2026, 10:10 a.m.