Triple

T6412418
Position Surface form Disambiguated ID Type / Status
Subject Anthony Perkins E127737 entity
Predicate spouse P13 FINISHED
Object Berry Berenson E538510 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: Berry Berenson | Statement: [Anthony Perkins, spouse, Berry Berenson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berry Berenson
Context triple: [Anthony Perkins, spouse, Berry Berenson]
  • A. Berry Berenson chosen
    Berry Berenson was an American photographer, actress, and model known for her work in film and fashion and for her marriage to actor Anthony Perkins.
  • B. Beryl David Rosofsky
    Beryl David Rosofsky was the birth name of Barney Ross, the famed American professional boxer and three-division world champion of the 1930s.
  • C. Sandy Lieberson
    Sandy Lieberson is a British film producer known for his influential work in 1970s and 1980s cinema and for helping develop emerging filmmakers and projects in the UK film industry.
  • D. Jean Berko Gleason
    Jean Berko Gleason is an American psycholinguist best known for her pioneering "wug test," which demonstrated how children acquire morphological rules in language.
  • E. Frances Berda
    Frances Berda was a composer best known for writing Nigeria’s former national anthem, “Nigeria, We Hail Thee.”
  • 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_69c0083723d88190b1e37b19df162c08 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c068d228208190ba05eeb7707482fe completed March 22, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640c48e688190981a19ce5eb2af44 completed March 27, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:42 p.m.