Triple

T15616518
Position Surface form Disambiguated ID Type / Status
Subject Pierre Savoye E375425 entity
Predicate familyName P18 FINISHED
Object Savoye E375425 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: Savoye | Statement: [Pierre Savoye, familyName, Savoye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savoye
Context triple: [Pierre Savoye, familyName, Savoye]
  • A. Savoye chosen
    Savoye is a French surname most notably associated with the family who commissioned Le Corbusier’s iconic modernist Villa Savoye.
  • B. Lubersac
    Lubersac is a small commune in the Corrèze department of south-central France, known for its rural character and traditional Limousin heritage.
  • C. Thoiry
    Thoiry is a commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
  • D. Noailles
    Noailles is a renowned art district in Croix-des-Bouquets, Haiti, famous for its vibrant community of metal sculptors and artisans.
  • E. Noailles
    Noailles is a prominent French noble family name historically associated with influential aristocrats, military leaders, and statesmen.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e980b748190b43c0b650bf1e629 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00758380d08190bfe73d3e052c1f0a completed May 10, 2026, 12:09 p.m.
Created at: April 10, 2026, 4:13 a.m.