Triple
T6619200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col de l’Iseran |
E149631
|
entity |
| Predicate | summitFacilities |
P27847
|
FINISHED |
| Object | restaurant or café in season |
—
|
LITERAL FINISHED |
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: restaurant or café in season | Statement: [Col de l’Iseran, summitFacilities, restaurant or café in season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: summitFacilities Context triple: [Col de l’Iseran, summitFacilities, restaurant or café in season]
-
A.
hasSummitFacility
chosen
Indicates that one entity possesses or provides a facility or infrastructure located at the summit of another entity (such as a mountain, hill, or peak).
-
B.
summitAccessibleFrom
Indicates that a summit can be reached or accessed starting from a specified location or route.
-
C.
summitShape
Indicates the geometric form or contour that characterizes the topmost point or summit of an object or landform.
-
D.
summitCount
Indicates the number of summits or peak ascents associated with an entity.
-
E.
summitView
Indicates a vantage point or perspective that is obtained from the top or highest point of something, such as a mountain or structure.
- 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_69c687ed8a9c81908bb671717cb192ef |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6bdb88cc881908f35648c15a7dc85 |
completed | March 27, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69c6ad007c1c8190af425f51011c7ad1 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:58 p.m.