Triple
T34484063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Hauā |
E885268
|
entity |
| Predicate | marae |
P37005
|
FINISHED |
| Object | Rukumoana Marae |
—
|
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: Rukumoana Marae | Statement: [Ngāti Hauā, marae, Rukumoana Marae]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marae Context triple: [Ngāti Hauā, marae, Rukumoana Marae]
-
A.
hasMarae
chosen
Indicates a relationship where an entity possesses, contains, or is associated with a marae (a Māori meeting place or communal space).
-
B.
hasWharenui
Indicates a relationship where an entity possesses or is associated with a wharenui (a Māori meeting house).
-
C.
avaroha
Indicates a descending movement or progression from a higher level, position, or pitch to a lower one.
-
D.
mastaba
Indicates a relationship where something is characterized as or functions as a mastaba, typically a flat-roofed, rectangular ancient tomb structure.
-
E.
haka
Indicates a performance or execution of a haka, typically as a ceremonial or expressive action directed toward or in the presence of others.
- 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71fb1ab3881908e2f7c0e6f23db49 |
completed | May 3, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 2:01 a.m.