Triple
T30397122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāi Tūāhuriri |
E773247
|
entity |
| Predicate | hasMaraeBuilding |
P144583
|
FINISHED |
| Object | wharenui at Tuahiwi Marae |
—
|
LITERAL 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: wharenui at Tuahiwi Marae | Statement: [Ngāi Tūāhuriri, hasMaraeBuilding, wharenui at Tuahiwi Marae]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaraeBuilding Context triple: [Ngāi Tūāhuriri, hasMaraeBuilding, wharenui at Tuahiwi Marae]
-
A.
hasMarae
Indicates a relationship where an entity possesses, contains, or is associated with a marae (a Māori meeting place or communal space).
-
B.
hasWharenui
chosen
Indicates a relationship where an entity possesses or is associated with a wharenui (a Māori meeting house).
-
C.
hasMāoriIwi
Indicates that an entity is associated with, or belongs to, a specific Māori iwi (tribe).
-
D.
hasMandapa
Indicates that a structure (typically a temple) includes or is associated with a mandapa, an attached or nearby pillared hall or pavilion used for rituals or gatherings.
-
E.
hasTaonga
Indicates a relationship where one entity possesses, holds, or is responsible for a taonga (a treasured or valued item, resource, or heritage).
- F. None of above.
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_69f2248facd48190b183c3f3ca6daef7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ff9e91bba08190af04b31ad815b13a |
completed | May 9, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69ff9e00e4808190bde8f07e6519a72c |
completed | May 9, 2026, 8:50 p.m. |
Created at: April 29, 2026, 8:03 p.m.