Triple

T14581067
Position Surface form Disambiguated ID Type / Status
Subject Collège de Beauvais E342192 entity
Predicate foundedBy P104 FINISHED
Object Jean de Beauvais E1129339 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: Jean de Beauvais | Statement: [Collège de Beauvais, foundedBy, Jean de Beauvais]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean de Beauvais
Context triple: [Collège de Beauvais, foundedBy, Jean de Beauvais]
  • A. Jean de Beauvais chosen
    Jean de Beauvais was a medieval French bishop and scholar after whom the Collège de Beauvais in Paris was named.
  • B. Guillaume de Berghes
    Guillaume de Berghes was a prominent early modern Catholic prelate who served as bishop in the Low Countries, notably holding the episcopal see of Ypres.
  • C. Benoît de Boigne
    Benoît de Boigne was an 18th–19th century Savoyard adventurer and general who made his fortune commanding armies in India before becoming a prominent benefactor in his native Chambéry.
  • D. Jean de Mailly
    Jean de Mailly was a 20th-century French architect known for his modernist designs and contributions to major urban projects in France.
  • E. Hervé de Crécy
    Hervé de Crécy is a French filmmaker and animator best known as one of the co-directors of the Oscar-winning animated short film "Logorama."
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb41e71748190a1deacc819dd26d3 completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe967e9c208190a00a82122b8c884c completed May 9, 2026, 2:05 a.m.
Created at: April 10, 2026, 1:24 a.m.