Triple
T27106310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richland Balsam |
E686587
|
entity |
| Predicate | overlookElevation |
P161857
|
FINISHED |
| Object | 1844 m |
—
|
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: 1844 m | Statement: [Richland Balsam, overlookElevation, 1844 m]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overlookElevation Context triple: [Richland Balsam, overlookElevation, 1844 m]
-
A.
overlookElevation
chosen
Indicates that one entity is positioned so as to have a higher vantage point from which it looks out over the elevation or raised area of another entity.
-
B.
elevation
Indicates the vertical height or altitude of one entity relative to a reference level or another entity.
-
C.
elevationApproxMeters
Indicates the approximate elevation of an entity above sea level, measured in meters.
-
D.
trailheadElevation
Indicates the elevation at which a trail begins, typically measured at its starting point or trailhead.
-
E.
elevationCoverageApproximate
Indicates an approximate or estimated representation of how elevation values are covered or distributed over a given area or dataset.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f623fdda548190827d6867bba39de7 |
completed | May 2, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 8:50 a.m.