Triple
T36038199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Policy and Planning unit |
E1042461
|
entity |
| Predicate | typeOfPolicyWork |
P178670
|
FINISHED |
| Object | provincial policy development |
—
|
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: provincial policy development | Statement: [Policy and Planning unit, typeOfPolicyWork, provincial policy development]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPolicyWork Context triple: [Policy and Planning unit, typeOfPolicyWork, provincial policy development]
-
A.
typeOfPolicyBody
Indicates that one entity is the governing or issuing body responsible for a particular policy type.
-
B.
grantedForWorkType
Indicates that a permission, license, or authorization is given specifically in connection with a particular type or category of work.
-
C.
tipoDePolíticas
chosen
Indicates a classification relationship where specific policies are associated with or assigned to a particular type or category of policies.
-
D.
typeOfWork
Indicates the kind or category of work associated with or performed by an entity.
-
E.
basedOnWorkTypeOftenAppearsIn
Indicates that something of a given work type frequently appears in or is commonly found within another context or medium.
- 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_69f76e2d7e8c8190bac4e90734566799 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a0226c8b2f881909de3c1a5ba40fc49 |
completed | May 11, 2026, 6:58 p.m. |
| PD | Predicate disambiguation | batch_6a0225602acc8190978ab4aacc615b8d |
completed | May 11, 2026, 6:52 p.m. |
Created at: May 3, 2026, 4:07 p.m.