Triple
T36614709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Kimihia |
E903570
|
entity |
| Predicate | isPartOfMāoriSocialStructure |
P201190
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Ngāti Kimihia, isPartOfMāoriSocialStructure, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfMāoriSocialStructure Context triple: [Ngāti Kimihia, isPartOfMāoriSocialStructure, yes]
-
A.
isTāngataWhenuaOf
Indicates that an entity is an indigenous person or people of, and holds ancestral ties and customary authority over, a particular place or land.
-
B.
hasMāoriIwi
Indicates that an entity is associated with, or belongs to, a specific Māori iwi (tribe).
-
C.
hasHapū
Indicates a relationship where an iwi (tribe) possesses, is composed of, or is associated with one or more hapū (sub-tribes).
-
D.
isKaitiakiOf
Indicates a guardianship or protective stewardship relationship in which one entity serves as the kaitiaki (guardian/caretaker) responsible for the care, protection, and wellbeing of another entity.
-
E.
hasMarae
Indicates a relationship where an entity possesses, contains, or is associated with a marae (a Māori meeting place or communal space).
- F. None of above. chosen
Provenance (4 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_69ffdd05d1908190957deb11392f4595 |
completed | May 10, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69ffdc0d33c881908b3483bee8a96540 |
completed | May 10, 2026, 1:14 a.m. |
| PDg | Predicate description generation | batch_69ffdd0486e08190a0f2ff4ce0aee13b |
completed | May 10, 2026, 1:19 a.m. |
Created at: May 3, 2026, 4:11 p.m.