Triple
T38607017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glacier Blanc |
E934369
|
entity |
| Predicate | usedAsNormalRouteFor |
P45128
|
FINISHED |
| Object | Dôme de Neige des Écrins |
—
|
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: Dôme de Neige des Écrins | Statement: [Glacier Blanc, usedAsNormalRouteFor, Dôme de Neige des Écrins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsNormalRouteFor Context triple: [Glacier Blanc, usedAsNormalRouteFor, Dôme de Neige des Écrins]
-
A.
usedRoutes
Indicates that an entity has utilized or traveled along specific routes.
-
B.
servesAsRouteTo
Indicates that one entity functions as a pathway, channel, or means of access leading to another entity.
-
C.
onStandardRouteOf
Indicates that something lies along or follows the usual, predefined, or officially designated route of another entity.
-
D.
currentUseOfRoute
Indicates that a particular route is presently being used for a specific purpose, activity, or traffic flow.
-
E.
isMostCommonRouteTo
chosen
Indicates that one route is the most frequently used or typical way to reach a particular destination or outcome compared to all other possible routes.
- 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_69f76eccd6d081909ccce171011739a1 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff32b88bf48190b45afd1b60cb511c |
completed | May 9, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69ff3031e18881908927b2ab452de863 |
completed | May 9, 2026, 1:01 p.m. |
Created at: May 3, 2026, 4:32 p.m.