Triple
T21961001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hokitika |
E542325
|
entity |
| Predicate | locatedSouthOf |
P9676
|
FINISHED |
| Object | Greymouth |
—
|
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: Greymouth | Statement: [Hokitika, locatedSouthOf, Greymouth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greymouth Context triple: [Hokitika, locatedSouthOf, Greymouth]
-
A.
Greymouth
chosen
Greymouth is a coastal town on New Zealand’s West Coast known for its gold-mining history, rugged scenery, and role as a regional service and transport hub.
-
B.
Kaikōura
Kaikōura is a coastal New Zealand town renowned for its dramatic mountain-and-sea scenery and world-class marine wildlife encounters, especially whale watching.
-
C.
Twizel
Twizel is a small town in New Zealand's Mackenzie District, known as a gateway to outdoor activities such as hiking, fishing, and stargazing in the surrounding alpine and lake landscapes.
-
D.
Wanganui
Wanganui is a city and surrounding region on New Zealand’s North Island, known for the Whanganui River and its strong rugby culture.
-
E.
Wanganui
Wanganui is a rural locality within the Byron Shire region of New South Wales, Australia.
- 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12455e99c819092ec59fe571f814e |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8 p.m.