Triple

T15566955
Position Surface form Disambiguated ID Type / Status
Subject The Soul Keeper E371140 entity
Predicate producer P490 FINISHED
Object Elda Ferri E935936 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: Elda Ferri | Statement: [The Soul Keeper, producer, Elda Ferri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elda Ferri
Context triple: [The Soul Keeper, producer, Elda Ferri]
  • A. Elda Ferri chosen
    Elda Ferri is an Italian film producer best known for her work on the acclaimed, Oscar-winning film "Life Is Beautiful."
  • B. Pilar Roldán
    Pilar Roldán is a Mexican fencer best known for taking the Olympic Oath for athletes and winning a silver medal in women's foil at the 1968 Mexico City Games.
  • C. Mora Fernández
    Mora Fernández is a Spanish-language surname most notably associated with Juan Mora Fernández, an early 19th-century Costa Rican politician and the country’s first head of state.
  • D. Inma Cuesta
    Inma Cuesta is a Spanish actress known for her work in film, television, and theater, often acclaimed for her dramatic roles in contemporary Spanish cinema.
  • E. Pilar García
    Pilar García was a high-ranking Cuban military and police officer who became notorious for his role in repressing opposition under Fulgencio Batista’s dictatorship.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04dde90b081908284d9258d4462e3 completed April 16, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbba9fb08190b800af317f0c9abf completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:10 a.m.