Triple

T21875758
Position Surface form Disambiguated ID Type / Status
Subject Le Miroir à deux faces E540140 entity
Predicate castMember P1668 FINISHED
Object Sandra Milo 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: Sandra Milo | Statement: [Le Miroir à deux faces, castMember, Sandra Milo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandra Milo
Context triple: [Le Miroir à deux faces, castMember, Sandra Milo]
  • A. Sandra Milo chosen
    Sandra Milo is an Italian actress best known for her collaborations with director Federico Fellini and her roles in classic 1960s Italian cinema.
  • B. Sandra Benes
    Sandra Benes is a key operations and data analyst on Moonbase Alpha in the science fiction television series "Space: 1999."
  • C. Marla Landi
    Marla Landi is an Italian-born British actress and television presenter best known for her film roles in the 1950s and 1960s and for appearing on the BBC children's program "Play School."
  • D. Sandra Voe
    Sandra Voe is a Scottish actress known for her work in film, television, and theatre, often appearing in character-driven dramas.
  • E. Sandra
    Sandra is a 1965 Italian drama film by Luchino Visconti, noted for its modern reworking of the Electra myth and its exploration of family secrets and guilt.
  • 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_69e0c479a98081908ce333853fdd4348 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0f33957f481908789b054a4fd1b77 completed April 28, 2026, 5:49 p.m.
Created at: April 16, 2026, 7:02 p.m.