Triple
T31466756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Māori Language Commission |
E802737
|
entity |
| Predicate | typeOfTaonga |
P201183
|
FINISHED |
| Object | living national taonga (Māori language) |
—
|
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: living national taonga (Māori language) | Statement: [Māori Language Commission, typeOfTaonga, living national taonga (Māori language)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfTaonga Context triple: [Māori Language Commission, typeOfTaonga, living national taonga (Māori language)]
-
A.
spearType
Indicates the specific kind or category of spear associated with an entity or action.
-
B.
typeOfPeg
Indicates that one entity is a specific kind or category of peg in relation to another entity.
-
C.
totemType
Indicates the specific category or kind of totem associated with an entity.
-
D.
isToolOf
Indicates that one entity functions as an instrument or means used by another entity to perform tasks or achieve goals.
-
E.
knifeName
Indicates that a particular name is assigned to or used for a given knife.
- 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_69f348c84c1c81908739f100ecf7394e |
completed | April 30, 2026, 12:19 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: April 30, 2026, 9:23 p.m.