Triple
T29651498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kennedy tax cut |
E750144
|
entity |
| Predicate | reducedCorporateTaxRateTo |
P76287
|
FINISHED |
| Object | 48% |
—
|
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: 48% | Statement: [Kennedy tax cut, reducedCorporateTaxRateTo, 48%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reducedCorporateTaxRateTo Context triple: [Kennedy tax cut, reducedCorporateTaxRateTo, 48%]
-
A.
reducedCorporateTaxRateFrom
Indicates that an entity’s corporate tax rate has been lowered starting from a specified prior rate or point in time.
-
B.
reducedTax
Indicates that an entity is subject to a lower-than-standard tax rate or tax burden.
-
C.
corporateTaxRate
chosen
Indicates the percentage of a corporation’s taxable income that is owed as tax under the applicable tax regime.
-
D.
reducedTopMarginalRateTo
Indicates that an entity has lowered the highest marginal rate (such as a top tax or interest rate) to a specified new level.
-
E.
reducedDutyRateOn
Indicates a relationship where a reduced customs or tax duty rate is applied to a specified item or transaction.
- 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_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 6:52 p.m.