Triple

T20440171
Position Surface form Disambiguated ID Type / Status
Subject Université Paul-Valéry Montpellier 3 E501364 entity
Predicate shortName P43 FINISHED
Object UPVM3 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: UPVM3 | Statement: [Université Paul-Valéry Montpellier 3, shortName, UPVM3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UPVM3
Context triple: [Université Paul-Valéry Montpellier 3, shortName, UPVM3]
  • A. UPVM3 chosen
    UPVM3 is a French public university in Montpellier specializing in arts, humanities, and social sciences, named after the writer and philosopher Paul Valéry.
  • B. VMU
    The VMU (Visual Memory Unit) is a memory card and secondary screen accessory for the Sega Dreamcast that provides game save storage and mini-game functionality.
  • C. UPVD
    UPVD is the commonly used acronym for the University of Perpignan Via Domitia, a French public university located in Perpignan.
  • D. VP30
    VP30 is a viral transcription factor protein of ebolaviruses that is essential for initiating and regulating the transcription of the viral genome.
  • E. VMC
    VMC is the Venus Monitoring Camera, a wide-angle imaging instrument on the European Space Agency’s Venus Express spacecraft used to study Venus’s atmosphere and cloud dynamics.
  • 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_69e0b4ab3cfc8190ac9bf32e932316b1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e685f20fe08190b9370b523a20153d completed April 20, 2026, 8 p.m.
Created at: April 16, 2026, 11:31 a.m.