Triple
T35436739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col de la Bonette |
E1024229
|
entity |
| Predicate | highestPointOfLoopRoad |
P140980
|
FINISHED |
| Object | 2802 m |
—
|
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: 2802 m | Statement: [Col de la Bonette, highestPointOfLoopRoad, 2802 m]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highestPointOfLoopRoad Context triple: [Col de la Bonette, highestPointOfLoopRoad, 2802 m]
-
A.
highestRoadPassIn
Indicates that a location contains the highest-elevation road pass within a specified area or region.
-
B.
highPointLocatedOn
Indicates that the highest point of one entity is situated on or atop another entity.
-
C.
highestPoint
Indicates that one entity is the point with the greatest elevation or height relative to another entity or defined area.
-
D.
summitRoadHighestElevation
chosen
Indicates that a given summit road reaches the highest elevation among comparable roads or within a specified area.
-
E.
highestPointFeature
Indicates that one entity is the feature or element that constitutes the highest point of another entity (such as a place, structure, or area).
- 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_69f76df743c48190aecb6dd79efb0d95 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 3, 2026, 4:04 p.m.