Triple
T36447523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Takapūwāhia Marae |
E897916
|
entity |
| Predicate | servesIwi |
P33500
|
FINISHED |
| Object | Ngāti Toa Rangatira |
—
|
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: Ngāti Toa Rangatira | Statement: [Takapūwāhia Marae, servesIwi, Ngāti Toa Rangatira]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesIwi Context triple: [Takapūwāhia Marae, servesIwi, Ngāti Toa Rangatira]
-
A.
servesOn
Indicates that one entity performs duties, functions, or holds a role as a member within another entity, such as a group, body, or organization.
-
B.
servesUnder
Indicates that one entity works in a subordinate role under the authority, command, or supervision of another entity.
-
C.
intendedToServe
chosen
Indicates that one entity was designed, planned, or purposed specifically to benefit, assist, or fulfill the needs of another entity.
-
D.
isServedAt
Indicates that something (such as food, drink, or a service) is provided or made available at a particular place or venue.
-
E.
servesUse
Indicates that one entity is used by or functions to serve the purpose or needs of 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_69f76e5720b481908f8177ac24a7560b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0045a7b4c081908e4dedabda7cf790 |
completed | May 10, 2026, 8:45 a.m. |
| PD | Predicate disambiguation | batch_6a0042b148a48190974b173f352e4b7f |
completed | May 10, 2026, 8:32 a.m. |
Created at: May 3, 2026, 4:10 p.m.