Triple
T17274847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geographe Bay |
E419359
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object | Dunsborough |
E286975
|
NE 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: Dunsborough | Statement: [Geographe Bay, hasNearbyTown, Dunsborough]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dunsborough Context triple: [Geographe Bay, hasNearbyTown, Dunsborough]
-
A.
Dunsborough
chosen
Dunsborough is a coastal holiday town in Western Australia known for its beaches, wineries, and proximity to the Margaret River region.
-
B.
Deloraine
Deloraine is a literary work that follows Cloudesley in the sequence of writings by the same author.
-
C.
Cundletown
Cundletown is a small riverside town in New South Wales, Australia, situated on the Manning River and known for its historic buildings and rural character.
-
D.
Wynyard
Wynyard is a coastal town in north-west Tasmania, Australia, known for its scenic beaches, nearby Table Cape, and role as a regional service and tourism hub.
-
E.
Wynyard
Wynyard is a major transport and commercial hub in central Sydney, best known for its busy railway station and surrounding office and retail precinct.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4332566c08190b4495dbbfe310ab6 |
completed | April 19, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180d08c9c8190ae139cd92720028a |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:40 a.m.