Triple

T2538475
Position Surface form Disambiguated ID Type / Status
Subject Gilles Deleuze E56326 entity
Predicate employer P7 FINISHED
Object Sorbonne E16381 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: Sorbonne | Statement: [Gilles Deleuze, employer, Sorbonne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sorbonne
Context triple: [Gilles Deleuze, employer, Sorbonne]
  • A. La Sorbonne chosen
    La Sorbonne is a historic university building in Paris that has long served as a central symbol of French higher education and intellectual life.
  • B. Sorbonne University
    Sorbonne University is a major public research university in Paris renowned for its historic humanities, science, and medical faculties.
  • C. Panthéon-Sorbonne University
    Panthéon-Sorbonne University is a prestigious Parisian institution renowned for its programs in law, humanities, and social sciences, and its historical roots in the University of Paris.
  • D. Université Paris 1 Panthéon-Sorbonne
    Université Paris 1 Panthéon-Sorbonne is a leading French public research university in Paris renowned for its programs in law, economics, humanities, and social sciences, and for its historic location in the Latin Quarter.
  • E. Sciences Po
    Sciences Po is a prestigious French university renowned for its programs in political science, international relations, and social sciences.
  • 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_69ab4a49b6508190bc467fbef4bac334 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd298fc2481908b2925bf6a06532b completed March 7, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69be92151b108190b415b7c6cf146b09 completed March 21, 2026, 12:41 p.m.
Created at: March 6, 2026, 9:47 p.m.