Triple
T26277498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Te Rūnanga o Ngāi Tahu Act 1996 |
E660613
|
entity |
| Predicate | iwiRepresented |
P54139
|
FINISHED |
| Object | Ngāi Tahu iwi |
—
|
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: Ngāi Tahu iwi | Statement: [Te Rūnanga o Ngāi Tahu Act 1996, iwiRepresented, Ngāi Tahu iwi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iwiRepresented Context triple: [Te Rūnanga o Ngāi Tahu Act 1996, iwiRepresented, Ngāi Tahu iwi]
-
A.
eraRepresented
Indicates that a subject depicts, symbolizes, or stands for a particular historical or temporal era.
-
B.
choseToRepresent
Indicates that one entity voluntarily decided to act on behalf of, or serve as a representative for, another entity or cause.
-
C.
isRepresentiveOf
Indicates that one entity serves as an official agent, spokesperson, or proxy acting on behalf of another entity.
-
D.
representedFor
Indicates that one entity has acted or served as the official representative or proxy on behalf of another entity.
-
E.
areRepresentedBy
chosen
Indicates that one entity serves as a representation, proxy, or stand-in for another entity.
- 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_69ee812960d081909cff6085cc9fa3a6 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e3641208190af80d23f7a692f3e |
completed | May 2, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 9:57 p.m.