Triple
T10230887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | President of Kazakhstan |
E243335
|
entity |
| Predicate | hasPowerToGrant |
P21124
|
FINISHED |
| Object | pardons |
—
|
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: pardons | Statement: [President of Kazakhstan, hasPowerToGrant, pardons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPowerToGrant Context triple: [President of Kazakhstan, hasPowerToGrant, pardons]
-
A.
grantedPower
Indicates that one entity has conferred authority, control, or a specific capability to another entity.
-
B.
typeOfPowerGranted
chosen
Indicates the specific kind or category of power or authority that is conferred from one entity to another.
-
C.
hasApprovalAuthority
Indicates that an entity possesses the power or right to review and formally approve or reject decisions, actions, or requests made by others.
-
D.
believedToGrant
Indicates that something is thought or assumed to provide, confer, or bestow a particular benefit, quality, or effect.
-
E.
hasExecutiveAuthority
Indicates that one entity holds formal decision-making and managerial power over an organization, group, or process.
- 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d23b620c8190b8a72d0eb0d16b93 |
completed | April 7, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69d4d1e9798c8190b437d53d48554ba1 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:19 a.m.