Triple

T20540584
Position Surface form Disambiguated ID Type / Status
Subject Université Paris-Sud E504318 entity
Predicate campus P269 FINISHED
Object Sceaux 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: Sceaux | Statement: [Université Paris-Sud, campus, Sceaux]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sceaux
Context triple: [Université Paris-Sud, campus, Sceaux]
  • A. Sceaux chosen
    Sceaux is a suburban commune in the southern outskirts of Paris, France, known for its historic château and expansive landscaped park.
  • B. Sceaux, France
    Sceaux, France is a suburban commune just south of Paris, known for its historic château, formal gardens designed by André Le Nôtre, and its role as a residence of French nobility.
  • C. Grimault
    Grimault is a French surname most notably borne by the influential animator and film director Paul Grimault.
  • D. Richepanse
    Richepanse is a French surname most notably borne by Antoine Richepanse, a general of the French Revolutionary and Napoleonic Wars.
  • E. Buré
    Buré is a small commune in the Orne department of northwestern France.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a29224f081908298d104161c5bb9 completed April 20, 2026, 10:02 p.m.
Created at: April 16, 2026, 11:37 a.m.