Triple

T17624564
Position Surface form Disambiguated ID Type / Status
Subject Rue Lepic E429803 entity
Predicate hasBuilding P105 FINISHED
Object Moulin de la Galette 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: Moulin de la Galette | Statement: [Rue Lepic, hasBuilding, Moulin de la Galette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moulin de la Galette
Context triple: [Rue Lepic, hasBuilding, Moulin de la Galette]
  • A. Moulin de la Galette chosen
    Moulin de la Galette is a historic windmill and former dance hall in Paris’s Montmartre district, long celebrated as a lively social hub and a favorite subject of Impressionist painters.
  • B. Salle des Capucines
    Salle des Capucines was the original name of the historic Parisian opera house now known as the Palais Garnier, a landmark of 19th-century French architecture and culture.
  • C. Moulin de Sannois
    Moulin de Sannois is a historic windmill in the town of Sannois, France, known as a prominent local heritage site and viewpoint.
  • D. Clos Montmartre
    Clos Montmartre is a small, historic urban vineyard in Paris’s Montmartre district, known for its limited-production wine and picturesque hillside setting.
  • E. Les Halles
    Les Halles is a major underground transport hub and commercial area in central Paris, historically known as the city’s main market district.
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbb2a348190982658d495c81da0 completed April 19, 2026, 5:52 a.m.
Created at: April 10, 2026, 5:52 a.m.