Triple
T32112401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Zealand economic policy |
E820150
|
entity |
| Predicate | structuralReformFocus |
P98268
|
FINISHED |
| Object | trade liberalisation |
—
|
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: trade liberalisation | Statement: [New Zealand economic policy, structuralReformFocus, trade liberalisation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: structuralReformFocus Context triple: [New Zealand economic policy, structuralReformFocus, trade liberalisation]
-
A.
structureFocus
Indicates that attention or emphasis is placed on the structural aspects or organization of something within the described context.
-
B.
goalOfReforms
Indicates that a reform or set of reforms is undertaken with the aim or intended objective of achieving a particular outcome.
-
C.
typeOfReforms
chosen
Indicates the specific kinds or categories of reforms associated with an entity or situation.
-
D.
associatedReform
Indicates a relationship where one entity is linked to, connected with, or involved in a particular reform or set of reforms.
-
E.
relatedReforms
Indicates that one reform is connected or associated with another reform, typically through shared goals, content, or impact.
- 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_69f3490209c881908ec0241476715f15 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b90568648190ac60ea9e5c686dfe |
completed | May 3, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:27 a.m.