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.