Triple
T12387307
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cambridge, New Zealand |
E295899
|
entity |
| Predicate | hasNearbyFeature |
P350
|
FINISHED |
| Object | Karapiro Dam |
E421529
|
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: Karapiro Dam | Statement: [Cambridge, New Zealand, hasNearbyFeature, Karapiro Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karapiro Dam Context triple: [Cambridge, New Zealand, hasNearbyFeature, Karapiro Dam]
-
A.
Karapiro Dam
chosen
Karapiro Dam is a major hydroelectric dam in New Zealand that forms Lake Karapiro and plays a key role in power generation and water management on the Waikato River.
-
B.
Tawa Dam
Tawa Dam is a major masonry dam in Madhya Pradesh, India, built on the Tawa River for irrigation, flood control, and hydroelectric power generation.
-
C.
Rapel Dam
Rapel Dam is a major hydroelectric and irrigation dam in central Chile that forms the Rapel Reservoir on the Rapel River.
-
D.
Pukaki Dam
Pukaki Dam is a major hydroelectric dam in New Zealand’s South Island that regulates Lake Pukaki as part of the Waitaki River power scheme.
-
E.
Arapuni Dam
Arapuni Dam is a major hydroelectric power station and concrete arch dam on New Zealand’s North Island, contributing significantly to the country’s renewable electricity generation.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbd489c819098233a111442762e |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ea3ec588190bca355953267578f |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 8, 2026, 9:54 p.m.