Triple
T18540530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerikeri |
E453085
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object | Kaikohe |
—
|
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: Kaikohe | Statement: [Kerikeri, hasNearbyTown, Kaikohe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaikohe Context triple: [Kerikeri, hasNearbyTown, Kaikohe]
-
A.
Kaikohe
chosen
Kaikohe is a small inland town in New Zealand known as the commercial and service hub of the Far North district.
-
B.
Pauanui
Pauanui is a popular coastal holiday town on New Zealand’s North Island, known for its sandy beach, boating, and relaxed resort atmosphere.
-
C.
Ke‘anae
Ke‘anae is a small, historic Hawaiian village on Maui’s rugged north shore, known for its taro fields, dramatic lava-rock coastline, and scenic ocean views.
-
D.
Hananui
Hananui is the Māori name for Mount Anglem, the highest peak on New Zealand’s Stewart Island/Rakiura and a prominent landmark in the region.
-
E.
Ku‘au
Ku‘au is a small coastal community on the north shore of Maui, Hawaii, known for its quiet residential feel and proximity to popular surf and windsurf spots.
- 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_69d8d387b5548190aa030dad2cb4947e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e534b64178819082861a03fd067095 |
completed | April 19, 2026, 8:01 p.m. |
Created at: April 10, 2026, 11:37 a.m.