Triple
T9021314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocas de Suesca |
E215729
|
entity |
| Predicate | bolting |
P85748
|
FINISHED |
| Object | sport routes with fixed protection |
—
|
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: sport routes with fixed protection | Statement: [Rocas de Suesca, bolting, sport routes with fixed protection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bolting Context triple: [Rocas de Suesca, bolting, sport routes with fixed protection]
-
A.
boltDesign
Indicates a design relationship where one entity specifies or defines the bolt configuration, features, or parameters used in another entity.
-
B.
binding
Indicates that one entity physically or chemically attaches, adheres, or forms a stable association with another entity.
-
C.
bore
Indicates that one entity caused another entity to feel uninterested, tired, or lacking in engagement.
-
D.
inning
Indicates a specific segment or period within a game during which a defined portion of play or action occurs.
-
E.
beam
Indicates that one entity emits, directs, or projects a concentrated line or stream (such as light, energy, or information) toward another entity.
- F. None of above. chosen
Provenance (4 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_69ca83a38aa88190bf1bb80c4548b5e2 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a43add08190983b7ac88576fd7e |
completed | April 1, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_69cc5edf84408190aa5f57cb8bfd00e1 |
completed | March 31, 2026, 11:55 p.m. |
| PDg | Predicate description generation | batch_69cc5f6dec4081909379bd57c02a5710 |
completed | March 31, 2026, 11:57 p.m. |
Created at: March 30, 2026, 7:07 p.m.