Triple
T17873689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prime Minister’s Office (New Zealand) |
E446895
|
entity |
| Predicate | supportsPolicyAreas |
P19912
|
FINISHED |
| Object | domestic policy |
—
|
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: domestic policy | Statement: [Prime Minister’s Office (New Zealand), supportsPolicyAreas, domestic policy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsPolicyAreas Context triple: [Prime Minister’s Office (New Zealand), supportsPolicyAreas, domestic policy]
-
A.
supportsPolicyArea
chosen
Indicates that one entity endorses, advocates for, or is in favor of a particular policy area or domain of public policy.
-
B.
supportsPolicy
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
-
C.
coversPolicyArea
Indicates that a policy, document, or initiative includes or addresses a particular policy area or topic within its scope.
-
D.
supportsMissionArea
Indicates that one entity contributes to, enables, or aligns with the objectives and activities of a specified mission area.
-
E.
hasPolicyArea
Indicates that an entity (such as a policy, program, or initiative) is associated with or pertains to a specific policy area or domain.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa4959881908774dafb7be99191 |
completed | April 19, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:18 a.m.