Triple

T31296426
Position Surface form Disambiguated ID Type / Status
Subject Arreau, Hautes-Pyrénées E798086 entity
Predicate locationDepictedRegion P64798 FINISHED
Object Hautes-Pyrénées 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: Hautes-Pyrénées | Statement: [Arreau, Hautes-Pyrénées, locationDepictedRegion, Hautes-Pyrénées]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locationDepictedRegion
Context triple: [Arreau, Hautes-Pyrénées, locationDepictedRegion, Hautes-Pyrénées]
  • A. primaryRegionDepicted
    Indicates that a resource primarily depicts or visually represents a particular geographic or spatial region as its main subject.
  • B. location depicted
    Indicates that one entity visually represents or shows the place where another entity is situated or occurs.
  • C. state of location depicted
    Indicates that the predicate specifies the condition or status of a particular place as shown or represented in some medium (e.g., an image, map, or description).
  • D. placeRegion chosen
    Indicates that a place is located within, or is part of, a larger geographic or administrative region.
  • E. placeDescribed
    Indicates that one entity provides a description or account of a particular place or location.
  • F. None of above.

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_69f224dfde288190af313f3c221c857e completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_6a017590e01c8190b985bb50cc6cd605 completed May 11, 2026, 6:22 a.m.
PD Predicate disambiguation batch_6a0175406b348190a5809b5f3497d46f completed May 11, 2026, 6:20 a.m.
Created at: April 29, 2026, 9:14 p.m.