Triple

T9814359
Position Surface form Disambiguated ID Type / Status
Subject Theodore Shapiro E238360 entity
Predicate hasCollaboratedWith P8554 FINISHED
Object Paul Feig E271298 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: Paul Feig | Statement: [Theodore Shapiro, hasCollaboratedWith, Paul Feig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Feig
Context triple: [Theodore Shapiro, hasCollaboratedWith, Paul Feig]
  • A. Paul Feig chosen
    Paul Feig is an American filmmaker, producer, and actor best known for directing hit comedies such as "Bridesmaids" and creating the cult TV series "Freaks and Geeks."
  • B. Paul Feigay
    Paul Feigay is a theatrical producer known for his work on the classic Broadway musical "On the Town."
  • C. Carol Holofcener
    Carol Holofcener is the mother of American film director and screenwriter Nicole Holofcener.
  • D. Anna Boden
    Anna Boden is an American filmmaker best known for co-directing the Marvel Studios superhero film "Captain Marvel" and for her long-time creative partnership with Ryan Fleck on independent dramas.
  • E. Marielle Heller
    Marielle Heller is an American filmmaker and actress best known for directing acclaimed character-driven films such as "The Diary of a Teenage Girl," "Can You Ever Forgive Me?," and "A Beautiful Day in the Neighborhood."
  • 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_69ca84defac48190abc1148804f184c1 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb2f19660819083e3f15780352052 completed April 2, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc67db68819093217c9a74e72fbf completed April 5, 2026, 2:43 a.m.
Created at: March 30, 2026, 8:30 p.m.