Triple
T19683584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Te Ata |
E472654
|
entity |
| Predicate | hasIwiRegister |
P4184
|
FINISHED |
| Object | Ngāti Te Ata membership register |
—
|
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: Ngāti Te Ata membership register | Statement: [Ngāti Te Ata, hasIwiRegister, Ngāti Te Ata membership register]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIwiRegister Context triple: [Ngāti Te Ata, hasIwiRegister, Ngāti Te Ata membership register]
-
A.
hasRegister
chosen
Indicates that one entity possesses, contains, or is associated with a specific register (such as a record, log, or hardware register).
-
B.
hasRegistrar
Indicates that an entity is formally recorded or overseen by a specific registrar organization or authority.
-
C.
hasRegisterSystem
Indicates that an entity uses or is associated with a particular register system (e.g., a system for recording, tracking, or registering items, events, or participants).
-
D.
hasStandardRegister
Indicates that something is expressed or occurs in a standard, neutral, or non-marked linguistic register.
-
E.
hasRegistrationAuthority
Indicates that an entity is formally overseen, recorded, or certified by a specific authority responsible for its registration.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e641c126b88190820281058a1e7793 |
completed | April 20, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69e53039ea808190a9106a53f564ab92 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:45 p.m.