Triple
T31883179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aberystwyth Cliff Railway |
E813934
|
entity |
| Predicate | hasAttractionAtSummit |
P8666
|
FINISHED |
| Object | camera obscura |
—
|
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: camera obscura | Statement: [Aberystwyth Cliff Railway, hasAttractionAtSummit, camera obscura]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAttractionAtSummit Context triple: [Aberystwyth Cliff Railway, hasAttractionAtSummit, camera obscura]
-
A.
hasSummitFacility
Indicates that one entity possesses or provides a facility or infrastructure located at the summit of another entity (such as a mountain, hill, or peak).
-
B.
hasSummitFeature
chosen
Indicates that a summit (or peak) possesses a particular characteristic, attribute, or notable feature.
-
C.
hasSummitViewsOf
Indicates that from the summit of one location, there are views overlooking or directed toward another location.
-
D.
hasSummitIn
Indicates that an entity (such as a mountain or organization) has its summit or peak located within a specified place or region.
-
E.
hasSummitTrail
Indicates that there exists a trail or route leading to the summit or highest point of a geographic feature.
- 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 30, 2026, 11:56 p.m.