Triple
T17288343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathedral Cove |
E419715
|
entity |
| Predicate | walkingTrackStartPoint |
P389
|
FINISHED |
| Object | Hahei Beach car park |
—
|
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: Hahei Beach car park | Statement: [Cathedral Cove, walkingTrackStartPoint, Hahei Beach car park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: walkingTrackStartPoint Context triple: [Cathedral Cove, walkingTrackStartPoint, Hahei Beach car park]
-
A.
startPoint
chosen
Indicates the initial location or position from which an object, path, or action begins.
-
B.
tracksLocation
Indicates that one entity monitors and records the geographic position or movement of another entity over time.
-
C.
tourStartingPoint
Indicates the location or point from which a tour begins.
-
D.
startPointLocatedIn
Indicates that the starting point of something is geographically or spatially located within a specified area or region.
-
E.
trackSystem
Indicates a relationship where one entity monitors, records, or follows the status, behavior, or changes of another entity within a system.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43781b7808190a0528ee9c54a0c66 |
completed | April 19, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69e3b0118ad08190b119cd219c68ba67 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:40 a.m.