Triple

T22094979
Position Surface form Disambiguated ID Type / Status
Subject Pierre Salvadori E546001 entity
Predicate notableWork P4 FINISHED
Object Après vous... 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: Après vous... | Statement: [Pierre Salvadori, notableWork, Après vous...]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Après vous...
Context triple: [Pierre Salvadori, notableWork, Après vous...]
  • A. Après vous... chosen
    Après vous... is a 2003 French romantic comedy film centered on a well-meaning head waiter whose attempt to save a stranger from suicide spirals into a series of complicated personal entanglements.
  • B. Après lui
    Après lui is a 2007 French drama film directed by Gaël Morel, centered on a grieving mother coping with the death of her son.
  • C. Hier encore
    "Hier encore" is a classic French chanson by Charles Aznavour reflecting nostalgically on lost youth and the passage of time.
  • D. Un an après
    Un an après is a reflective autobiographical work by French actress and writer Anne Wiazemsky, in which she recounts a pivotal period of her life and career.
  • E. Petit à petit
    Petit à petit is a 1970 ethnographic comedy film by Jean Rouch that satirically explores cultural differences through the story of Nigerien businessmen investigating life in Paris.
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e82c1481908701f255b834f192 completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.