Triple

T20154779
Position Surface form Disambiguated ID Type / Status
Subject Byron Kennedy E491526 entity
Predicate employer P7 FINISHED
Object Kennedy Miller — 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: Kennedy Miller | Statement: [Byron Kennedy, employer, Kennedy Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kennedy Miller
Context triple: [Byron Kennedy, employer, Kennedy Miller]
  • A. Kennedy Miller Mitchell chosen
    Kennedy Miller Mitchell is an Australian film and television production company best known for works like the Mad Max series and other acclaimed screen projects.
  • B. John Miller
    John Miller is a prominent American sports journalist and television anchor best known for his work on ESPN’s “20/20” sports coverage and related broadcasts.
  • C. John Miller
    John Miller was an American politician who became the inaugural governor of the U.S. state of North Dakota after its admission to the Union.
  • D. John Miller
    John Miller is an American politician who served as a U.S. Representative from Washington before being succeeded by Maria Cantwell.
  • E. John Miller
    John Miller was a mountaineer known for making the first recorded ascent of Banner Peak in the Sierra Nevada.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667df7ac081908816d2d29e7c6513 completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.