Triple

T19456227
Position Surface form Disambiguated ID Type / Status
Subject RoboCop (2014 film) E486738 entity
Predicate castMember P1668 FINISHED
Object Michael Keaton 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 Keaton | Statement: [RoboCop (2014 film), castMember, Michael Keaton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Keaton
Context triple: [RoboCop (2014 film), castMember, Michael Keaton]
  • A. Michael Keaton chosen
    Michael Keaton is an American actor known for his versatile performances in films such as "Batman," "Beetlejuice," and the Academy Award–winning "Birdman."
  • B. Jonathan Irons
    Jonathan Irons is the primary villain in Call of Duty: Advanced Warfare, a powerful private military CEO who seeks to reshape global politics through force.
  • C. Jonathan Irons
    Jonathan Irons is an American man whose wrongful conviction and eventual release from prison drew national attention, in part due to the advocacy and later marriage of WNBA star Maya Moore.
  • D. Adam West
    Adam West was an American actor best known for his iconic portrayal of Batman in the 1960s television series.
  • E. Burt Ward
    Burt Ward is an American actor best known for playing Robin, the Boy Wonder, in the 1960s Batman television series.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c4088881908f23f25a82a513f6 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:38 p.m.