Triple
T14855972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wineglass Bay Lookout |
E349349
|
entity |
| Predicate | hasApproximateDistanceFromCarPark |
P38511
|
FINISHED |
| Object | 1.3 km one way |
—
|
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: 1.3 km one way | Statement: [Wineglass Bay Lookout, hasApproximateDistanceFromCarPark, 1.3 km one way]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateDistanceFromCarPark Context triple: [Wineglass Bay Lookout, hasApproximateDistanceFromCarPark, 1.3 km one way]
-
A.
hasParkingNearby
Indicates that a location has one or more parking facilities or spaces available within a close surrounding area.
-
B.
hasApproximateDrivingDistanceFrom
chosen
Indicates that one entity is located at an estimated or approximate driving distance from another entity, typically measured along road routes rather than as a precise or exact value.
-
C.
hasParkingFor
Indicates that a place or facility provides designated parking spaces suitable for a specified type of vehicle or user.
-
D.
hasParking
Indicates that a place or facility provides designated parking space(s) available for use.
-
E.
proximityToLandmark
Indicates a spatial relationship where one entity is located near or close to a specified landmark.
- 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_69d822ed7e1881909b90fca143ad7e34 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded44458ec8190be295a95f5daab14 |
completed | April 14, 2026, 11:56 p.m. |
| PD | Predicate disambiguation | batch_69de8c1798c08190b433e9ad21e41a42 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:54 a.m.