Triple

T6742731
Position Surface form Disambiguated ID Type / Status
Subject Tim Bevan E154126 entity
Predicate coFounderWith P2835 FINISHED
Object Eric Fellner E136678 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: Eric Fellner | Statement: [Tim Bevan, coFounderWith, Eric Fellner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eric Fellner
Context triple: [Tim Bevan, coFounderWith, Eric Fellner]
  • A. Eric Fellner chosen
    Eric Fellner is a British film producer and co-chairman of Working Title Films, known for overseeing numerous successful UK and international movies.
  • B. Eric Pohlmann
    Eric Pohlmann was an Austrian-born character actor best known for providing the original voice of the villain Ernst Stavro Blofeld in the early James Bond films.
  • C. Eric Schoffstall
    Eric Schoffstall is a software developer best known for creating Gulp, a popular JavaScript-based task runner used in web development build workflows.
  • D. Bill Steinkellner
    Bill Steinkellner is an American television writer and producer best known for his work on popular sitcoms, often in collaboration with his wife Cheri Steinkellner.
  • E. Brian Roettinger
    Brian Roettinger is an American graphic designer and art director known for his innovative work in music packaging and visual identities for prominent artists and brands.
  • 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_69c6880d84d8819095d19de2295f26ac completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1b3b1448190a94b4b64f01af14a completed March 27, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7eeb79b9c819084738c207aa5c62d completed March 28, 2026, 3:07 p.m.
Created at: March 27, 2026, 2:10 p.m.