Triple
T36614707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Kimihia |
E903570
|
entity |
| Predicate | traditionalPeopleOf |
P100744
|
FINISHED |
| Object | Aotearoa New Zealand |
—
|
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: Aotearoa New Zealand | Statement: [Ngāti Kimihia, traditionalPeopleOf, Aotearoa New Zealand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalPeopleOf Context triple: [Ngāti Kimihia, traditionalPeopleOf, Aotearoa New Zealand]
-
A.
traditionalPeople
chosen
Indicates that the subject consists of or is associated with people who maintain long-established customs, beliefs, or ways of life.
-
B.
metIndigenousPeople
Indicates that an entity has encountered or come into contact with Indigenous people.
-
C.
traditionalCountry
Indicates that a country is characterized by long-established customs, cultural practices, and social norms that have been preserved over time.
-
D.
riverinePeople
Indicates a relationship where people live along, depend on, or are closely associated with rivers and river environments.
-
E.
ethnicGroupDepicted
Indicates that a particular ethnic group is visually represented or portrayed in the subject entity (such as an image, artwork, or media item).
- 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_69f76e6960e4819092047756ceb9a17e |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff9b1ad27081908f8a492396950795 |
completed | May 9, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69ff9a6354c48190ae21070c1424cb7a |
completed | May 9, 2026, 8:34 p.m. |
Created at: May 3, 2026, 4:11 p.m.