Triple
T25314308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pointe Hélène |
E634691
|
entity |
| Predicate | isPartOfRidge |
P91361
|
FINISHED |
| Object | Grandes Jorasses main ridge |
—
|
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: Grandes Jorasses main ridge | Statement: [Pointe Hélène, isPartOfRidge, Grandes Jorasses main ridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfRidge Context triple: [Pointe Hélène, isPartOfRidge, Grandes Jorasses main ridge]
-
A.
isRidge
Indicates that something has the form or function of a ridge, typically being a long, narrow raised or elevated feature relative to its surroundings.
-
B.
isOnRidgeWith
Indicates that two or more entities are located together along the same ridge or elevated crest.
-
C.
isOnRidgeBetween
Indicates that something is located on the ridge that lies between two other reference points or areas.
-
D.
hasRidgeRoute
Indicates that one entity possesses or is associated with a route that follows or traverses a ridge.
-
E.
associatedWithRidge
chosen
Indicates that one entity has a spatial, structural, or contextual connection or relationship to a ridge.
- 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_69e75a9847c08190bb02990d06d5ffb7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f67c9fe7b48190b79b4041357edb49 |
completed | May 2, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 21, 2026, 1:27 p.m.