Triple

T18410189
Position Surface form Disambiguated ID Type / Status
Subject Lescot Wing E441735 entity
Predicate namedAfter P63 FINISHED
Object Pierre Lescot 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: Pierre Lescot | Statement: [Lescot Wing, namedAfter, Pierre Lescot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pierre Lescot
Context triple: [Lescot Wing, namedAfter, Pierre Lescot]
  • A. Pierre Lescot chosen
    Pierre Lescot was a 16th-century French Renaissance architect best known for designing major portions of the Louvre Palace in Paris.
  • B. Élie Lescot
    Élie Lescot was a Haitian politician who led the country as its president during the early 1940s, overseeing Haiti through much of World War II.
  • C. François Mansart
    François Mansart was a pioneering 17th-century French architect known for helping to establish the classical Baroque style in France and popularizing the mansard roof.
  • D. Philippe Goujon
    Philippe Goujon is a French politician known for serving as a long-time local leader in Paris and as a member of the National Assembly.
  • E. Philibert de l'Orme
    Philibert de l'Orme was a leading 16th-century French Renaissance architect and theorist known for his innovative designs and influential architectural treatises.
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e5195b98808190b9cfb2e444f2b524 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:47 a.m.