Triple
T17056491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alex Txikon |
E413833
|
entity |
| Predicate | hasClimbedAbove |
P77843
|
FINISHED |
| Object | 8000 metres |
—
|
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: 8000 metres | Statement: [Alex Txikon, hasClimbedAbove, 8000 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasClimbedAbove Context triple: [Alex Txikon, hasClimbedAbove, 8000 metres]
-
A.
hasClimbFrom
Indicates a relationship where one location or object serves as the starting point from which a climb or ascent to another location or object begins.
-
B.
hasFirstRecordedAscent
Indicates that a particular ascent is the earliest known or documented successful climb of a specific route, peak, or climbing objective.
-
C.
mountainHeightClimbed
chosen
Indicates the height of a mountain that has been climbed by an entity.
-
D.
highestPeakClimbed
Indicates the tallest mountain or peak that an entity has successfully climbed.
-
E.
attemptedAscentOf
Indicates an action where an entity makes an effort to climb or ascend another entity, regardless of whether the ascent is completed successfully.
- 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_69d886cde3d481908d4d01ba88ba7eb7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3db7a96288190bd985f79c3f55623 |
completed | April 18, 2026, 7:28 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:34 a.m.