Triple

T22142381
Position Surface form Disambiguated ID Type / Status
Subject Harry Goldfarb E547194 entity
Predicate hasRomanticPartner P9994 FINISHED
Object Marion Silver 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: Marion Silver | Statement: [Harry Goldfarb, hasRomanticPartner, Marion Silver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Silver
Context triple: [Harry Goldfarb, hasRomanticPartner, Marion Silver]
  • A. Marion Silver chosen
    Marion Silver is a troubled young woman whose descent into drug addiction and shattered dreams forms one of the central storylines in the psychological drama film "Requiem for a Dream."
  • B. Marion Marshall
    Marion Marshall was an American film actress who appeared in numerous Hollywood movies from the 1940s through the 1960s.
  • C. Marion Edwards
    Marion Edwards was the wife of American film and television actor Robert Cummings.
  • D. Marion Leonard
    Marion Leonard was an early American silent film actress and one of the first stars of director D. W. Griffith’s Biograph company.
  • E. Marion Nichols
    Marion Nichols is an individual notable enough to be recognized as a distinguished bearer of the surname Nichols, though specific widely known public details about them are limited.
  • 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_69e11e3a95d88190a3bd80d9471976c3 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129bf78108190b50d937917258693 completed April 28, 2026, 9:42 p.m.
Created at: April 16, 2026, 8:32 p.m.