Triple
T20049916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whangārei District |
E499165
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Maunu |
—
|
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: Maunu | Statement: [Whangārei District, contains, Maunu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maunu Context triple: [Whangārei District, contains, Maunu]
-
A.
Maunu
chosen
Maunu is a residential suburb located on the southwestern outskirts of Whangārei in New Zealand’s Northland Region.
-
B.
Mauna Kea
Mauna Kea is a dormant volcano on Hawaii’s Big Island renowned both as the state’s tallest mountain and as one of the world’s premier sites for astronomical observatories.
-
C.
Mauna Loa
Mauna Loa is one of the world’s largest and most active shield volcanoes, dominating much of Hawaii’s Big Island.
-
D.
Mauna Kahalawai
Mauna Kahalawai, also known as the West Maui Mountains, is an eroded shield volcano forming the rugged western portion of the Hawaiian island of Maui.
-
E.
Mount Waiʻaleʻale
Mount Waiʻaleʻale is a shield volcano and one of the wettest spots on Earth, located near the center of the Hawaiian island of Kauaʻi.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6632cccb481908278c8b2930a8c26 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:37 p.m.