Triple
T17288512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karangahake Gorge |
E419719
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Paeroa |
E392342
|
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: Paeroa | Statement: [Karangahake Gorge, locatedNear, Paeroa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paeroa Context triple: [Karangahake Gorge, locatedNear, Paeroa]
-
A.
Paeroa
chosen
Paeroa is a small New Zealand town in the Waikato region, best known as the birthplace of the L&P soft drink and its historic gold-mining heritage.
-
B.
Nausori
Nausori is a town in Fiji located near the capital Suva on the island of Viti Levu, known for its airport and role as a regional commercial center.
-
C.
Yipounou
Yipounou is an alternate name for Yipunu, a Bantu language spoken primarily by the Punu people of Gabon.
-
D.
Tofua
Tofua is a volcanic island in Tonga known for its active caldera, rugged terrain, and historical role in the aftermath of the HMS Bounty mutiny.
-
E.
Tuatapere
Tuatapere is a small rural town in New Zealand’s Southland region, known as a gateway to the Hump Ridge Track and for its forestry and farming heritage.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43781b7808190a0528ee9c54a0c66 |
completed | April 19, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a017957c738819087341bcd51b55114 |
completed | May 11, 2026, 6:38 a.m. |
Created at: April 10, 2026, 5:40 a.m.