Triple
T35436738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col de la Bonette |
E1024229
|
entity |
| Predicate | hasLoopRoadAroundSummit |
P148612
|
FINISHED |
| Object | Cime de la Bonette |
—
|
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: Cime de la Bonette | Statement: [Col de la Bonette, hasLoopRoadAroundSummit, Cime de la Bonette]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLoopRoadAroundSummit Context triple: [Col de la Bonette, hasLoopRoadAroundSummit, Cime de la Bonette]
-
A.
hasLoopRoad
chosen
Indicates that a location or area is connected by a road that forms a closed loop, beginning and ending at the same point.
-
B.
hasSummitRoad
Indicates that there exists a road providing access to the summit or highest point of a geographic feature or structure.
-
C.
hasSummitOnSideOf
Indicates that the summit or highest point of one geographic feature is located on the side of another feature.
-
D.
hasSummitTrail
Indicates that there exists a trail or route leading to the summit or highest point of a geographic feature.
-
E.
hasSummitTunnel
Indicates that a summit or peak contains or is traversed by a tunnel.
- 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_69ff234f32888190a1d800a3bda432eb |
completed | May 9, 2026, 12:06 p.m. |
| PD | Predicate disambiguation | batch_69ff228ae9a0819083f4b97c10b923f4 |
completed | May 9, 2026, 12:03 p.m. |
Created at: May 3, 2026, 4:04 p.m.