Triple

T9968828
Position Surface form Disambiguated ID Type / Status
Subject Max Rockatansky E195751 entity
Predicate creator P184 FINISHED
Object Byron Kennedy E491526 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: Byron Kennedy | Statement: [Max Rockatansky, creator, Byron Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Byron Kennedy
Context triple: [Max Rockatansky, creator, Byron Kennedy]
  • A. Byron Kennedy chosen
    Byron Kennedy was an Australian film producer best known for co-creating and producing the original Mad Max films with director George Miller.
  • B. Byron Hadley
    Byron Hadley is a brutal and authoritarian prison guard captain from Stephen King’s novella “Rita Hayworth and Shawshank Redemption” and its film adaptation “The Shawshank Redemption.”
  • C. Jack McFarland
    Jack McFarland is a flamboyant, aspiring actor and Will Truman’s exuberant best friend on the sitcom "Will & Grace," known for his over-the-top personality and comedic antics.
  • D. John Bryan
    John Bryan was an American statesman who represented South Carolina as a delegate to the Continental Congress during the Revolutionary era.
  • E. John Bryan
    John Bryan was a British film art director and production designer known for his visually distinctive work on mid-20th-century cinema.
  • 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_69ca82ebd1288190912f9e4482d1fa35 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7b683ac8190ac97bd775a860d29 completed April 2, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d281e1eb848190b898e36ec9821228 completed April 5, 2026, 3:38 p.m.
Created at: March 30, 2026, 8:47 p.m.