Triple

T15425074
Position Surface form Disambiguated ID Type / Status
Subject Mary Costa E369487 entity
Predicate name P16 FINISHED
Object Mary Costa E369487 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: Mary Costa | Statement: [Mary Costa, name, Mary Costa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Costa
Context triple: [Mary Costa, name, Mary Costa]
  • A. Mary Costa chosen
    Mary Costa is an American operatic soprano and actress best known for providing the voice of Princess Aurora in Disney's animated film "Sleeping Beauty."
  • B. Eileen Pardee
    Eileen Pardee is known as the former spouse of Anthony Dryden Marshall, the American theatrical producer and son of philanthropist Brooke Astor.
  • C. Loretta Castorini
    Loretta Castorini is the practical, widowed Italian-American bookkeeper at the heart of the romantic comedy film "Moonstruck," whose unexpected love affair upends her carefully ordered life.
  • D. Paula Alquist
    Paula Alquist is the psychologically tormented heroine of the 1944 film "Gaslight," whose manipulation by her husband gave rise to the term "gaslighting."
  • E. Rose Gacioch
    Rose Gacioch was a standout outfielder and pitcher in the All-American Girls Professional Baseball League, best known for her time with the Rockford Peaches.
  • 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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ec1fb288190a3625b8e4f487dd1 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb7921208190bbf4e1a01c6ec5ee completed May 10, 2026, 2:20 a.m.
Created at: April 10, 2026, 3:20 a.m.