Triple

T18510142
Position Surface form Disambiguated ID Type / Status
Subject The Mothman Prophecies E452316 entity
Predicate producer P490 FINISHED
Object Tom Rosenberg 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: Tom Rosenberg | Statement: [The Mothman Prophecies, producer, Tom Rosenberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Rosenberg
Context triple: [The Mothman Prophecies, producer, Tom Rosenberg]
  • A. Tom Rosenberg chosen
    Tom Rosenberg is an American film producer and co-founder of Lakeshore Entertainment, known for backing numerous successful Hollywood films.
  • B. William Rosenberg
    William Rosenberg was an American entrepreneur best known for creating the coffee and doughnut chain that became Dunkin' Donuts.
  • C. Ken Rosenberg
    Ken Rosenberg is a neurotic, fast-talking criminal lawyer and associate of the protagonist in the Grand Theft Auto series, most prominently featured in Vice City.
  • D. Dave Rosenberg
    Dave Rosenberg is a technology entrepreneur best known as a co-founder of MuleSoft, a leading integration and API management platform company.
  • E. Don Ressler
    Don Ressler is an American entrepreneur and co-founder of several online fashion and e-commerce ventures, best known for building subscription-based retail brands.
  • 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_69d8d386df84819092355ebb260d848e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e533457e608190988304bf8bc2db1c completed April 19, 2026, 7:55 p.m.
Created at: April 10, 2026, 11:36 a.m.