Triple
T26320049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toulouse–Latour-de-Carol line |
E662080
|
entity |
| Predicate | connectsMountainRegion |
P76788
|
FINISHED |
| Object | Ariège Pyrenees |
—
|
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: Ariège Pyrenees | Statement: [Toulouse–Latour-de-Carol line, connectsMountainRegion, Ariège Pyrenees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsMountainRegion Context triple: [Toulouse–Latour-de-Carol line, connectsMountainRegion, Ariège Pyrenees]
-
A.
mountainAccess
Indicates that an entity has the ability, right, or means to reach, enter, or utilize a mountain or mountainous area.
-
B.
shareMountainRange
Indicates that two geographic entities are located within or along the same mountain range.
-
C.
associatedWithMountainRange
chosen
Indicates a relationship where something is connected or related in some way to a specific mountain range.
-
D.
mountainRange
Indicates that one entity is a mountain range that the other entity is part of, associated with, or located in.
-
E.
borderMountainOf
Indicates that a mountain lies along or forms part of the border of a specified region or entity.
- 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_69ee812e73048190aae587f1d51e5a06 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f7431c0eec81909ead443e07d75e18 |
completed | May 3, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69f74143cf708190a12d487884298437 |
completed | May 3, 2026, 12:36 p.m. |
Created at: April 26, 2026, 10:27 p.m.