Triple
T29651501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kennedy tax cut |
E750144
|
entity |
| Predicate | sponsoredByAdministration |
P86
|
FINISHED |
| Object | Kennedy administration |
—
|
NE NERFINISHED |
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: Kennedy administration | Statement: [Kennedy tax cut, sponsoredByAdministration, Kennedy administration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sponsoredByAdministration Context triple: [Kennedy tax cut, sponsoredByAdministration, Kennedy administration]
-
A.
proposesAdministrationBy
Indicates that one entity formally suggests that another entity should be responsible for administering or managing something.
-
B.
administeredBy
chosen
Indicates that an action, service, or process is carried out, managed, or overseen by a specified agent or authority.
-
C.
administersFrom
Indicates that an action, service, or process is carried out or managed starting from a particular source, location, or authority.
-
D.
administeredAs
Indicates that one entity is given or applied to another entity as a treatment, dose, or intervention.
-
E.
administeredFor
Indicates that something (typically a treatment, medication, or intervention) is given or applied to an entity for a specific purpose, condition, or intended effect.
- 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f676f968d08190a4adba0439b438c9 |
completed | May 2, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69f675ff62c48190a634bbb8896973b9 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 28, 2026, 6:52 p.m.