Triple

T22172056
Position Surface form Disambiguated ID Type / Status
Subject Two Girls and a Sailor E547946 entity
Predicate starring P1507 FINISHED
Object Ava Gardner 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: Ava Gardner | Statement: [Two Girls and a Sailor, starring, Ava Gardner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ava Gardner
Context triple: [Two Girls and a Sailor, starring, Ava Gardner]
  • A. Ava Gardner chosen
    Ava Gardner was a celebrated American film actress and Hollywood icon of the 1940s and 1950s, renowned for her beauty, charisma, and roles in classics such as "The Killers" and "Mogambo."
  • B. Gloria Grahame
    Gloria Grahame was an American film actress known for her sultry screen presence and acclaimed roles in classic Hollywood films noir and dramas of the 1940s and 1950s.
  • C. Lizabeth Scott
    Lizabeth Scott was an American film actress known for her sultry voice and frequent roles as a femme fatale in 1940s and 1950s film noir.
  • D. Audrey Wyler
    Audrey Wyler is a central character in Stephen King’s novel "Desperation," known for her possession and manipulation by the malevolent entity Tak.
  • E. Lauren Bacall
    Lauren Bacall was an iconic American film and stage actress known for her sultry voice, striking looks, and classic roles in 1940s Hollywood noir films.
  • 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_69e11e3d53f88190a2b690e3f25bb062 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a68c26c8190b1258595bd96cb63 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.