Triple
T25036758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia Board of Pardons and Paroles |
E626997
|
entity |
| Predicate | canDeny |
P19799
|
FINISHED |
| Object | parole |
—
|
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: parole | Statement: [Georgia Board of Pardons and Paroles, canDeny, parole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canDeny Context triple: [Georgia Board of Pardons and Paroles, canDeny, parole]
-
A.
isDeniedBy
Indicates that a request, claim, or action directed at an entity is explicitly refused or rejected by another entity.
-
B.
canEnforce
Indicates that one entity has the authority or capability to compel compliance with rules, decisions, or obligations upon another entity.
-
C.
canRejectWith
Indicates that one entity has the authority or ability to refuse, decline, or dismiss another entity or proposal using a specific method or condition.
-
D.
typicallyDenies
chosen
Indicates that an entity, in most usual or common circumstances, refuses, rejects, or does not grant something to another entity.
-
E.
canAuthorize
Indicates that one entity has the power or permission to grant approval or official permission for another entity to perform an action or access a resource.
- 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_69e2ff2a2c088190be513727ee8bfe78 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f4530674d88190a3516bbd64234111 |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:08 a.m.