Triple

T22446417
Position Surface form Disambiguated ID Type / Status
Subject Xavier Leroy E554873 entity
Predicate workInstitution P1203 FINISHED
Object Inria 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: Inria | Statement: [Xavier Leroy, workInstitution, Inria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Inria
Context triple: [Xavier Leroy, workInstitution, Inria]
  • A. INRIA chosen
    INRIA is the French national research institute dedicated to computer science and applied mathematics, known for its leading contributions to digital science and technology.
  • B. Laboratoire Ampère
    Laboratoire Ampère is a French research laboratory associated with INSA Lyon that focuses on electrical engineering, automation, and related applied sciences.
  • C. LORIA
    LORIA is a French research laboratory specializing in computer science and information technologies, jointly operated by several institutions in the Lorraine region.
  • D. Laboratoire de Recherche en Informatique
    Laboratoire de Recherche en Informatique is a French computer science research laboratory known for its work in theoretical computer science, formal methods, and related areas.
  • E. Lyon research center
    The Lyon research center is a major French Petroleum Institute facility specializing in research and development in petroleum, energy, and related technologies.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4803908190990280ebd258cb03 completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:47 p.m.