Triple
T33238771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archives New Zealand |
E850905
|
entity |
| Predicate | typeOfRecordsManaged |
P140174
|
FINISHED |
| Object | government records |
—
|
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: government records | Statement: [Archives New Zealand, typeOfRecordsManaged, government records]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfRecordsManaged Context triple: [Archives New Zealand, typeOfRecordsManaged, government records]
-
A.
typeOfRecordsHeld
chosen
Indicates the kinds or categories of records that an entity maintains or possesses.
-
B.
typeOfPropertyManaged
Indicates the specific category or kind of property that an entity is responsible for managing.
-
C.
recordsManagedBy
Indicates that certain records are overseen, maintained, or administered by a specified managing entity.
-
D.
classificationTypeManaged
Indicates that the classification type is controlled or administered through a managed process or system rather than being assigned freely or ad hoc.
-
E.
numberOfPropertiesManaged
Indicates the total count of properties that an entity is responsible for managing.
- 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_69f349613f988190a1eb75467d167122 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a00a602b6b48190a9dea8ae22d2fa05 |
completed | May 10, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_6a00a559bf3881909a7b50776d8f47bb |
completed | May 10, 2026, 3:33 p.m. |
Created at: May 1, 2026, 1:31 a.m.