Triple
T29814031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biancograt route on Piz Bernina |
E757052
|
entity |
| Predicate | approachInvolves |
P10363
|
FINISHED |
| Object | glacier ascent |
—
|
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: glacier ascent | Statement: [Biancograt route on Piz Bernina, approachInvolves, glacier ascent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approachInvolves Context triple: [Biancograt route on Piz Bernina, approachInvolves, glacier ascent]
-
A.
approaches
Indicates that one entity moves closer in position or state to another entity or reference point.
-
B.
includesApproach
chosen
Indicates that one entity incorporates, utilizes, or is characterized by a particular method, strategy, or approach in relation to another entity or context.
-
C.
usedToApproach
Indicates that one entity employed another entity as a means or method to move closer to or reach a target entity or location.
-
D.
guardedApproachTo
Indicates a cautious, defensive, or wary manner of moving toward or engaging with another entity.
-
E.
formsApproachTo
Indicates that one entity develops or establishes a particular method, strategy, or way of dealing with or addressing another entity or situation.
- 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_69f2245701c88190ad42415a0956c4ed |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd864235b481908738dbb69556bc62 |
completed | May 8, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69fd8373b6bc819091c554f29ee17fec |
completed | May 8, 2026, 6:32 a.m. |
Created at: April 29, 2026, 5:25 p.m.