Triple

T22899518
Position Surface form Disambiguated ID Type / Status
Subject The Bone Collector E568269 entity
Predicate starredActor P5563 FINISHED
Object Michael Rooker 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: Michael Rooker | Statement: [The Bone Collector, starredActor, Michael Rooker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Rooker
Context triple: [The Bone Collector, starredActor, Michael Rooker]
  • A. Michael Rooker chosen
    Michael Rooker is an American actor best known for his roles as Yondu in the Marvel Cinematic Universe and Merle Dixon in the television series The Walking Dead.
  • B. Cliff Smith
    Cliff Smith is an actor known for his role in the film "The Breaks."
  • C. Brion James
    Brion James was an American character actor best known for his distinctive roles in science fiction and action films, including his memorable performance as the replicant Leon in "Blade Runner."
  • D. William Fichtner
    William Fichtner is an American character actor known for his intense, often villainous or morally complex roles in films such as "Heat," "Armageddon," and "Black Hawk Down," as well as the TV series "Prison Break."
  • E. Jon Hale
    Jon Hale is an English football executive best known for serving as chairman of Hereford FC.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180155b1c8190a83eb6ec45387a1a completed April 29, 2026, 3:50 a.m.
Created at: April 17, 2026, 3:41 p.m.