Triple

T2419112
Position Surface form Disambiguated ID Type / Status
Subject Gérard Huet E52376 entity
Predicate notableStudent P4838 FINISHED
Object Gilles Dowek E46385 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: Gilles Dowek | Statement: [Gérard Huet, notableStudent, Gilles Dowek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gilles Dowek
Context triple: [Gérard Huet, notableStudent, Gilles Dowek]
  • A. Gilles Dowek chosen
    Gilles Dowek is a French logician and computer scientist known for his influential work in proof theory, type systems, and automated deduction.
  • B. Thierry Coquand
    Thierry Coquand is a French logician and computer scientist known for his work on type theory, constructive mathematics, and the development of the calculus of constructions.
  • C. Gordon Plotkin
    Gordon Plotkin is a British computer scientist renowned for his foundational contributions to programming language semantics and domain theory.
  • D. Luca Cardelli
    Luca Cardelli is an Italian computer scientist known for his influential work in type theory, programming language design, and the development of the Modula-3 and Polyphonic C# languages.
  • E. Markus Wenzel
    Markus Wenzel is a computer scientist best known as the primary developer of the Isabelle proof assistant.
  • 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_69ab495622948190bc6bc6e4cddaf645 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc96e1b3881909de57501b5d4099a completed March 7, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0a299648190a55e9f2c47bd307f completed March 9, 2026, 4:09 p.m.
Created at: March 6, 2026, 9:42 p.m.