Triple

T21812387
Position Surface form Disambiguated ID Type / Status
Subject Berry Berenson E538510 entity
Predicate spouse P13 FINISHED
Object Anthony Perkins 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: Anthony Perkins | Statement: [Berry Berenson, spouse, Anthony Perkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Perkins
Context triple: [Berry Berenson, spouse, Anthony Perkins]
  • A. Anthony Perkins chosen
    Anthony Perkins was an American actor best known for his iconic role as Norman Bates in Alfred Hitchcock’s film "Psycho."
  • B. Alan Bates
    Alan Bates was an acclaimed English actor known for his intense, nuanced performances in film, television, and theatre from the 1960s onward.
  • C. Vincent E. Price
    Vincent E. Price is an American political communication scholar and academic leader who serves as the president of Duke University.
  • D. Arthur Caan
    Arthur Caan is the son of the late American actor James Caan, known for his iconic roles in films such as "The Godfather."
  • E. Vincent Price
    Vincent Price was an American actor renowned for his distinctive voice and charismatic presence, particularly in classic horror films and gothic dramas.
  • 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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07cc7ec1c8190a5420b44a49ae32f completed April 28, 2026, 9:24 a.m.
Created at: April 16, 2026, 6:53 p.m.