Triple
T19303018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katikati |
E482748
|
entity |
| Predicate | hasNearbyLocality |
P3883
|
FINISHED |
| Object | Waihi Beach |
—
|
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: Waihi Beach | Statement: [Katikati, hasNearbyLocality, Waihi Beach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waihi Beach Context triple: [Katikati, hasNearbyLocality, Waihi Beach]
-
A.
Waihi Beach
chosen
Waihi Beach is a popular coastal town and holiday destination on New Zealand’s Bay of Plenty, known for its long sandy surf beach and relaxed seaside atmosphere.
-
B.
Wainui Beach
Wainui Beach is a popular surf and swimming beach near Gisborne on New Zealand’s North Island, known for its consistent waves and scenic sandy coastline.
-
C.
Onetangi Beach
Onetangi Beach is a long, sandy surf beach and popular holiday destination on Waiheke Island in New Zealand’s Hauraki Gulf.
-
D.
Paihia Beach
Paihia Beach is a popular sandy shoreline in New Zealand’s Bay of Islands, known for its calm waters, swimming, and water-based activities.
-
E.
Eimeo Beach
Eimeo Beach is a scenic coastal beach near Mackay in Queensland, Australia, known for its palm-fringed shoreline and views over the Coral Sea.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc8add788190aed98bcbad518808 |
completed | April 20, 2026, 10:14 a.m. |
Created at: April 10, 2026, 1:31 p.m.