Triple
T36448482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Te Whatu Ora – Health New Zealand |
E897942
|
entity |
| Predicate | replacesStructure |
P10258
|
FINISHED |
| Object | 20 district health boards |
—
|
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: 20 district health boards | Statement: [Te Whatu Ora – Health New Zealand, replacesStructure, 20 district health boards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacesStructure Context triple: [Te Whatu Ora – Health New Zealand, replacesStructure, 20 district health boards]
-
A.
replacedStructure
chosen
Indicates that one structure has been substituted for, or taken the place of, another structure.
-
B.
replacedStructureType
Indicates that one structure type has been substituted or superseded by another structure type.
-
C.
replacedStructureAtLocation
Indicates that one structure has been substituted for another at a specific location.
-
D.
replacedStructureDamagedBy
Indicates that a structure which has been replaced is (or was) damaged by a specified agent, event, or condition.
-
E.
managesStructure
Indicates that one entity is responsible for overseeing, organizing, or administering the operation and maintenance of a particular structure.
- 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_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: May 3, 2026, 4:10 p.m.