Triple
T36818245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Porou |
E909805
|
entity |
| Predicate | signedTreatySettlement |
P123310
|
FINISHED |
| Object | Ngāti Porou Deed of Settlement |
—
|
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 Porou Deed of Settlement | Statement: [Ngāti Porou, signedTreatySettlement, Ngāti Porou Deed of Settlement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signedTreatySettlement Context triple: [Ngāti Porou, signedTreatySettlement, Ngāti Porou Deed of Settlement]
-
A.
treatySettlementInstrument
Indicates that a treaty serves as the formal legal instrument by which a settlement or agreement between parties is established or implemented.
-
B.
hasTreatySettlementWith
chosen
Indicates the existence of a formal treaty-based agreement or settlement between two parties.
-
C.
signedTreatyAt
Indicates that an entity formally entered into and endorsed a treaty at a specific location.
-
D.
confirmedTreaty
Indicates that an entity has formally approved, ratified, or validated a treaty, making the agreement officially recognized or in force.
-
E.
resultOfTreaties
Indicates that something exists, occurs, or holds true as a consequence or outcome of one or more treaties.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca9591e48190a5a5bdb5d72ae4b3 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:13 p.m.