Triple

T10514977
Position Surface form Disambiguated ID Type / Status
Subject Logorama E248007 entity
Predicate writtenBy P806 FINISHED
Object François Alaux E1037386 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: François Alaux | Statement: [Logorama, writtenBy, François Alaux]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: François Alaux
Context triple: [Logorama, writtenBy, François Alaux]
  • A. François Alaux chosen
    François Alaux is a French filmmaker best known for co-directing the Oscar-winning animated short film "Logorama."
  • B. Jacques Villeglé
    Jacques Villeglé was a French artist best known for his torn poster collages that transformed urban street advertisements into politically and socially charged works of art.
  • C. René Guiette
    René Guiette was a Belgian painter and art critic associated with modernist movements in the early 20th century.
  • D. Marie-Dominique Culioli
    Marie-Dominique Culioli is a French woman best known as the first wife of former French president Nicolas Sarkozy.
  • E. Louis Marie Turreau
    Louis Marie Turreau was a French Revolutionary general notorious for leading the brutal "infernal columns" campaign that devastated the Vendée region during the War in the Vendée.
  • 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_69d381c4aa948190942e1d803143fb0e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509cbacb08190a446c864b97823ad completed April 7, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7304bc684819083ca999f283b0cb3 completed May 3, 2026, 11:23 a.m.
Created at: April 6, 2026, 12:27 p.m.