Triple
T27031514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandakphu–Phalut trail |
E680930
|
entity |
| Predicate | hasElevationMax |
P46534
|
FINISHED |
| Object | Sandakphu 3636 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: Sandakphu 3636 m | Statement: [Sandakphu–Phalut trail, hasElevationMax, Sandakphu 3636 m]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasElevationMax Context triple: [Sandakphu–Phalut trail, hasElevationMax, Sandakphu 3636 m]
-
A.
elevationRangeUpperBound
Indicates the maximum elevation value that bounds the upper limit of an elevation range for something.
-
B.
hasTopElevation
chosen
Indicates that an entity has a specified maximum or highest elevation value.
-
C.
peakElevationMetres
Indicates the maximum height of an entity above sea level, measured in metres.
-
D.
hasMainPeakElevation_m
Indicates the relationship that specifies the elevation, in meters, of the main or highest peak associated with an entity.
-
E.
highestPassApproxElevation
Indicates the approximate elevation of the highest pass along a given route or within a specified area.
- 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_69eeeb5566f08190813daf896fa3da04 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f657f653448190a945b4751af8507d |
completed | May 2, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 7:14 a.m.