Triple
T26767242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glacier d’Estellette |
E674972
|
entity |
| Predicate | slopeOf |
P83773
|
FINISHED |
| Object | Aiguille de Tré la Tête |
—
|
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: Aiguille de Tré la Tête | Statement: [Glacier d’Estellette, slopeOf, Aiguille de Tré la Tête]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: slopeOf Context triple: [Glacier d’Estellette, slopeOf, Aiguille de Tré la Tête]
-
A.
slopeUse
Indicates how a particular slope or gradient is utilized or purposed in relation to another entity.
-
B.
slopeType
Indicates the classification of a slope based on its geometric or physical characteristics, such as steepness, shape, or orientation.
-
C.
correctorSlopeComputation
Indicates the computation of the slope used in a corrector step within an iterative or numerical correction process.
-
D.
isOnSlopeOf
chosen
Indicates that one entity is located on the inclined surface or side of another entity, typically a sloping terrain or structure.
-
E.
usesWeightedAverageOfSlopes
Indicates that something is determined or calculated by taking a weighted average of multiple slope values.
- 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_69eecda85298819097ee1c38a3d772e7 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6192a12ac8190a92158e548f4d5c8 |
completed | May 2, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 4 a.m.