Triple

T2498215
Position Surface form Disambiguated ID Type / Status
Subject King Vidor E52400 entity
Predicate directed P7373 FINISHED
Object Ruby Gentry E359534 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: Ruby Gentry | Statement: [King Vidor, directed, Ruby Gentry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruby Gentry
Context triple: [King Vidor, directed, Ruby Gentry]
  • A. Ruby Gentry chosen
    Ruby Gentry is a 1952 American melodrama film directed by King Vidor, starring Jennifer Jones as a poor Southern woman whose passionate love and social struggles lead to tragedy.
  • B. Gwendolyn Rickard
    Gwendolyn Rickard was the longtime wife of American actor and dancer Ray Bolger, best known for his role as the Scarecrow in "The Wizard of Oz."
  • C. Anne Ashmond
    Anne Ashmond is a fictional character appearing in the film "Royal Wedding."
  • D. Alice Kincaid
    Alice Kincaid is a fictional character known as the daughter of Lemon Breeland in the television series "Hart of Dixie."
  • E. Katherine Green
    Katherine Green is a film editor known for her work on the romantic comedy "40 Days and 40 Nights."
  • 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_69ab4957b3a88190adf968ae0c1b931c completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1ae9040819091b3ca5b98659e99 completed March 7, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69b367dc88ac81909e73e290c745b8be completed March 13, 2026, 1:26 a.m.
Created at: March 6, 2026, 9:46 p.m.