Triple
T19674883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salt Ash |
E472426
|
entity |
| Predicate | isNear |
P350
|
FINISHED |
| Object | Williamtown |
—
|
NE NERFINISHED |
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: Williamtown | Statement: [Salt Ash, isNear, Williamtown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Williamtown Context triple: [Salt Ash, isNear, Williamtown]
-
A.
Williamtown
chosen
Williamtown is a locality in New South Wales, Australia, best known for hosting Newcastle Airport and the RAAF Base Williamtown military air base.
-
B.
Reynella
Reynella is a suburban locality in Adelaide, South Australia, known for its residential character and historical association with the region’s early wine industry.
-
C.
Maryborough
Maryborough is a historic city in Queensland, Australia, known for its heritage architecture and role as a regional service and transport hub.
-
D.
Springston
Springston is a small rural township in New Zealand’s Canterbury region, located within the Selwyn District near Christchurch.
-
E.
Narooma
Narooma is a coastal town in New South Wales, Australia, known for its scenic beaches, fishing, and proximity to Montague Island.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e641bb2b7c8190b2badf12ce2caa52 |
completed | April 20, 2026, 3:09 p.m. |
Created at: April 10, 2026, 1:45 p.m.