Triple
T23720324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Two-thousanders of Canada |
E586122
|
entity |
| Predicate | elevationRangeType |
P1977
|
FINISHED |
| Object | medium-elevation mountains |
—
|
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: medium-elevation mountains | Statement: [Two-thousanders of Canada, elevationRangeType, medium-elevation mountains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevationRangeType Context triple: [Two-thousanders of Canada, elevationRangeType, medium-elevation mountains]
-
A.
typicalElevationRange
chosen
Indicates the usual range of elevation values within which something commonly occurs or exists.
-
B.
elevationRangeUpperBound
Indicates the maximum elevation value that bounds the upper limit of an elevation range for something.
-
C.
elevationType
Indicates the kind or classification of elevation associated with an entity, such as how its height or altitude is characterized.
-
D.
altitudeRange_m
Indicates the range of altitudes, measured in meters, over which the relationship or condition holds.
-
E.
mountainRangeType
Indicates the classification or category of a mountain range based on its geological or geographical type.
- 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b910759c8190be189db3e86d7258 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7 p.m.