Triple
T3656064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarence Town |
E77532
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Dungog |
E20271
|
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: Dungog | Statement: [Clarence Town, nearbyTown, Dungog]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dungog Context triple: [Clarence Town, nearbyTown, Dungog]
-
A.
Dungog
chosen
Dungog is a small rural town in New South Wales, Australia, known for its historic architecture, dairy farming, and proximity to the Barrington Tops National Park.
-
B.
Woolgoolga
Woolgoolga is a coastal town in New South Wales, Australia, known for its beaches, Sikh community, and banana plantations.
-
C.
Menindee
Menindee is a small town in western New South Wales, Australia, known for its historic river port heritage and proximity to the Menindee Lakes system.
-
D.
Inverell
Inverell is a rural town in northern New South Wales, Australia, known for its sapphire mining and agricultural production.
-
E.
Boorowa
Boorowa is a rural town in New South Wales, Australia, known for its rich agricultural surroundings and heritage streetscapes.
- 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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3bc2b408190a3a51f9cde5a03b5 |
completed | March 8, 2026, 6:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5f59074e881908d346937da0b056e |
completed | March 14, 2026, 11:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.