Triple
T22817758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linda Glacier route |
E565144
|
entity |
| Predicate | hasAscentStyle |
P45129
|
FINISHED |
| Object | one-day push from Plateau Hut |
—
|
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: one-day push from Plateau Hut | Statement: [Linda Glacier route, hasAscentStyle, one-day push from Plateau Hut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAscentStyle Context triple: [Linda Glacier route, hasAscentStyle, one-day push from Plateau Hut]
-
A.
hasAscentCharacter
Indicates that something possesses a particular type or quality of ascent, such as how it rises, climbs, or increases.
-
B.
typicalAscentStyle
chosen
Indicates the usual or characteristic manner or technique by which an ascent or climb is performed.
-
C.
approximateAscent
Indicates an estimated or non-exact upward change or increase in value, level, or position.
-
D.
hasCommonAscentCombination
Indicates that two or more entities share the same combination of ancestral origins or lineage paths.
-
E.
hasStyle
Indicates that an entity possesses, exhibits, or is characterized by a particular style or manner.
- 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dcd7da481909d591f145382725b |
completed | April 29, 2026, 3:41 a.m. |
| PD | Predicate disambiguation | batch_69eed2cb30f481909566369f515f6eff |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:33 p.m.