Triple
T12581889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waikato |
E300358
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Tokoroa |
E293576
|
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: Tokoroa | Statement: [Waikato, hasTown, Tokoroa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokoroa Context triple: [Waikato, hasTown, Tokoroa]
-
A.
Tokoroa
chosen
Tokoroa is a forestry-based town in New Zealand’s North Island known for its timber industry and location between Rotorua and Taupō.
-
B.
Tokoroa High School
Tokoroa High School is a secondary school serving the educational needs of students in the town of Tokoroa, New Zealand.
-
C.
Tokoroa Rugby Football Club
Tokoroa Rugby Football Club is a local rugby union club based in Tokoroa, New Zealand, competing in regional competitions and serving as a community hub for the sport.
-
D.
Pukeatua
Pukeatua is a rural locality in New Zealand’s Waikato region, known for its farming landscape and proximity to the Maungatautari ecological reserve.
-
E.
Onerahi
Onerahi is a coastal suburb of Whangārei in Northland, New Zealand, known for its harbour views and proximity to Whangārei Airport.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954b97a508190b6c901c506441dd0 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6559ba5108190b85be540a405eec8 |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 9, 2026, 5:02 p.m.