Triple

T13510131
Position Surface form Disambiguated ID Type / Status
Subject Contact E321116 entity
Predicate producer P490 FINISHED
Object Steve Starkey E184375 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: Steve Starkey | Statement: [Contact, producer, Steve Starkey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Starkey
Context triple: [Contact, producer, Steve Starkey]
  • A. Steve Starkey chosen
    Steve Starkey is an American film producer best known for his longtime collaboration with director Robert Zemeckis on major Hollywood films.
  • B. Ollie Starkey
    Ollie Starkey is a key playable character in Compulsion Games’ dystopian action-adventure title "We Happy Few," known for his gruff demeanor and resistance to the drug-fueled conformity of Wellington Wells.
  • C. Lee Boardman
    Lee Boardman is a British actor known for his roles in television dramas such as Rome and Coronation Street.
  • D. Terry Oldfield
    Terry Oldfield is a British composer and multi-instrumentalist best known for his atmospheric, flute-led new-age and world music, and for being the brother and frequent collaborator of musician Mike Oldfield.
  • E. Roy Marples
    Roy Marples is a software engineer best known for his work on the OpenRC init system and various networking tools in the Linux and BSD ecosystems.
  • 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_69d807629d6c8190998f1b9bb12d2ed0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaf86a6208190be8c18f7a0158f23 completed April 12, 2026, 2:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75490291c8190b5985d8c90ef1af6 completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:43 p.m.