Triple
T36447590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaukau |
E897918
|
entity |
| Predicate | isAncestralTo |
P369
|
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: [Kaukau, isAncestralTo, Ngāti Toa Rangatira]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAncestralTo Context triple: [Kaukau, isAncestralTo, Ngāti Toa Rangatira]
-
A.
hasAncestralTo
Indicates that one entity is an ancestor of another, existing in an earlier generation within a lineage or heritage chain.
-
B.
isAncestralNameOf
Indicates that one name is historically or genealogically derived from, or serves as the origin for, another name.
-
C.
hasAncestor
chosen
Indicates that one entity is an ancestor (direct or indirect, such as a parent, grandparent, etc.) of another entity in a genealogical or hierarchical lineage.
-
D.
destinedAncestorOf
Indicates that one entity is fated or preordained to become an ancestor of another entity in the future.
-
E.
hasAncestralType
Indicates that one type is derived from, or originates from, another more primitive or original type in an inheritance or lineage hierarchy.
- 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_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.