Triple

T20900720
Position Surface form Disambiguated ID Type / Status
Subject Superman: Doomsday E514660 entity
Predicate composer P1361 FINISHED
Object Robert J. Kral 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: Robert J. Kral | Statement: [Superman: Doomsday, composer, Robert J. Kral]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert J. Kral
Context triple: [Superman: Doomsday, composer, Robert J. Kral]
  • A. Robert J. Kral chosen
    Robert J. Kral is an Australian-born composer best known for his atmospheric and dramatic scores for television series such as the Buffy the Vampire Slayer spin-off Angel.
  • B. Richard C. Kratina
    Richard C. Kratina was a cinematographer best known for his work on the 1977 horror film "The Sentinel."
  • C. John R. Petrocik
    John R. Petrocik is an American political scientist known for his influential work on voting behavior, party coalitions, and electoral realignment in the United States.
  • D. Michael E. Bakich
    Michael E. Bakich is an American astronomy writer, editor, and popularizer of observational astronomy, long associated with Astronomy magazine.
  • E. Stephen D. Mastrofski
    Stephen D. Mastrofski is an American criminologist known for his influential research on policing practices and critical evaluations of theories such as broken windows policing.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8fa5228819084341dbc813cc1e3 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.