Triple

T23375461
Position Surface form Disambiguated ID Type / Status
Subject Pulp E593594 entity
Predicate hasMember P10 FINISHED
Object Steve Mackey 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: Steve Mackey | Statement: [Pulp, hasMember, Steve Mackey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Mackey
Context triple: [Pulp, hasMember, Steve Mackey]
  • A. Steve Mackey chosen
    Steve Mackey is an English musician and record producer best known as the longtime bassist of the band Pulp and for his work with various alternative and pop artists.
  • B. Stephen Mack
    Stephen Mack was an early 19th-century American businessman and older brother of Lucy Mack Smith, making him the maternal uncle of Latter-day Saint founder Joseph Smith.
  • C. Rich McKay
    Rich McKay is an American football executive best known for his long tenure in NFL leadership roles, including as a team executive and influential member of league committees.
  • D. Steven McKay
    Steven McKay is a film and television screenwriter best known for his work on the boxing drama movie "Diggstown."
  • E. Daren Ackwood
    Daren Ackwood is a fictional character portrayed by actor Daren Kagasoff, likely in a television or film production.
  • 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b2fe9081909cc002abe50dad2a completed April 29, 2026, 6:22 a.m.
Created at: April 17, 2026, 5:33 p.m.