Triple

T20740682
Position Surface form Disambiguated ID Type / Status
Subject The Last Kiss (2006 film) E510429 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 Last Kiss (2006 film), producer, Tom Rosenberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Rosenberg
Context triple: [The Last Kiss (2006 film), 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_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c20e76ac8190985203b2c17aca14 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:32 p.m.