Triple
T5250426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eiger |
E118572
|
entity |
| Predicate | northFaceFirstAscentDate |
P8812
|
FINISHED |
| Object | 1938-07-24 |
—
|
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: 1938-07-24 | Statement: [Eiger, northFaceFirstAscentDate, 1938-07-24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: northFaceFirstAscentDate Context triple: [Eiger, northFaceFirstAscentDate, 1938-07-24]
-
A.
firstWinterAscentBy
Indicates that the subject was first successfully climbed in winter conditions by the specified person or party.
-
B.
firstAscentBy
Indicates the person or party that first successfully ascended or climbed a particular route, peak, or feature.
-
C.
firstRecordedAsClimbedBy
Indicates the person or group who is credited with making the first recorded ascent of a particular climb or peak.
-
D.
firstAscentFrom
Indicates the starting location or route from which the first successful ascent of something (typically a peak or climb) was made.
-
E.
firstAscentYear
chosen
Indicates the calendar year in which something (typically a route, peak, or climb) was first successfully ascended.
- 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b79ae0c81908a9b8614f6886259 |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.