Triple

T7987022
Position Surface form Disambiguated ID Type / Status
Subject Curtains E185706 entity
Predicate directedBy P7373 FINISHED
Object Scott Ellis E524174 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: Scott Ellis | Statement: [Curtains, directedBy, Scott Ellis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scott Ellis
Context triple: [Curtains, directedBy, Scott Ellis]
  • A. Scott Ellis chosen
    Scott Ellis is an American theater director and producer known for his acclaimed work on numerous Broadway revivals and new productions.
  • B. Mike Eley
    Mike Eley is a British cinematographer known for his work on acclaimed films and television dramas.
  • C. Michael Jessop
    Michael Jessop is a member of the Derby Philosophical Society, a learned society dedicated to scientific and intellectual inquiry in Derby, England.
  • D. Greg Mathieson
    Greg Mathieson is an American keyboardist, composer, and producer known for his work in jazz, fusion, and pop music, collaborating with numerous prominent artists.
  • E. Steve Harnett
    Steve Harnett is a member of the band Helmet, contributing to the influential American alternative metal group known for its heavy, precise sound.
  • 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_69ca829a2cfc819083d591d58ec04075 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c4d11b08190aa13afb17155462c completed March 31, 2026, 3:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc568393008190b8ff6cc17f9b5c46 completed March 31, 2026, 11:19 p.m.
Created at: March 30, 2026, 5:15 p.m.