Triple
T11151817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patea |
E263804
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Te Wahipounamu |
E532931
|
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: Te Wahipounamu | Statement: [Patea, partOf, Te Wahipounamu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Te Wahipounamu Context triple: [Patea, partOf, Te Wahipounamu]
-
A.
Takapō
Takapō is the Māori name for Lake Tekapo, a renowned turquoise glacial lake in New Zealand’s South Island celebrated for its alpine scenery and dark-sky stargazing.
-
B.
Te Waipounamu
chosen
Te Waipounamu is the Māori name for New Zealand’s South Island, renowned for its dramatic landscapes, including mountains, plains, and coastal regions.
-
C.
Marakei
Marakei is a coral atoll in the Pacific island nation of Kiribati, known for its traditional villages and encircling lagoon.
-
D.
Whangamatā
Whangamatā is a popular coastal holiday town on New Zealand’s North Island, known for its surf beaches, fishing, and relaxed seaside atmosphere.
-
E.
Te Puia
Te Puia is a major Māori cultural and geothermal tourism center in Rotorua, New Zealand, renowned for its geysers, hot springs, and traditional arts and crafts institute.
- 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8719e74819095413abc6c79296c |
completed | April 9, 2026, 5:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4422ea8748190856d461e741193b9 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 8, 2026, 9:28 p.m.