Triple

T14171015
Position Surface form Disambiguated ID Type / Status
Subject Maverick Records E351206 entity
Predicate coFounder P2835 FINISHED
Object Ronald L. Perelman E264938 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: Ronald L. Perelman | Statement: [Maverick Records, coFounder, Ronald L. Perelman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ronald L. Perelman
Context triple: [Maverick Records, coFounder, Ronald L. Perelman]
  • A. Ronald Perelman chosen
    Ronald Perelman is an American billionaire investor and corporate raider best known for building a vast business empire through leveraged buyouts and his long-time control of Revlon.
  • B. Louis M. Silverstein
    Louis M. Silverstein is a film producer known for his work on the comedy movie "Strange Brew."
  • C. Stanley Rubin
    Stanley Rubin was an American film and television producer known for his work on numerous Hollywood features and TV series from the 1940s through the 1980s.
  • D. Howard Milstein
    Howard Milstein is an American businessman and real estate developer known for leading Milstein Properties and serving as chairman of New York Private Bank & Trust.
  • E. Benjamin Glazer
    Benjamin Glazer was an Academy Award–winning American screenwriter, producer, and director active during the early decades of Hollywood cinema.
  • 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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61b472288190b4a271daa54aa6cd completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd193f85e88190b37a37747ec9d019 completed May 7, 2026, 10:59 p.m.
Created at: April 10, 2026, 1:01 a.m.