Triple

T12420170
Position Surface form Disambiguated ID Type / Status
Subject Paula Weinstein E296746 entity
Predicate employer P7 FINISHED
Object Spring Creek Productions E286414 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: Spring Creek Productions | Statement: [Paula Weinstein, employer, Spring Creek Productions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spring Creek Productions
Context triple: [Paula Weinstein, employer, Spring Creek Productions]
  • A. Spring Creek Productions chosen
    Spring Creek Productions is a film production company known for backing major Hollywood features, including the political war thriller "Blood Diamond."
  • B. Cross Creek Pictures
    Cross Creek Pictures is an American film production company known for financing and producing critically acclaimed movies such as "Black Swan."
  • C. Morningside Productions
    Morningside Productions is a film production company best known for producing fantasy and adventure movies in the mid-20th century.
  • D. Sunflower Productions
    Sunflower Productions is a film production company known for producing the historical drama "The New World."
  • E. Sky Productions
    Sky Productions is a television production company best known for co-producing the action-packed drama series "Strike Back."
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d6efd748190a5d9396a343e41e1 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f634933b9881909fd592ede7c3e49c completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:55 p.m.