Triple
T23038899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Revenue Act of 1926 |
E573681
|
entity |
| Predicate | topMarginalIncomeTaxRateAfterAct |
P37501
|
FINISHED |
| Object | 25% |
—
|
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: 25% | Statement: [Revenue Act of 1926, topMarginalIncomeTaxRateAfterAct, 25%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topMarginalIncomeTaxRateAfterAct Context triple: [Revenue Act of 1926, topMarginalIncomeTaxRateAfterAct, 25%]
-
A.
topMarginalIndividualIncomeTaxRateAppliesTo
Indicates that the specified top marginal individual income tax rate is applicable to the referenced taxpayer or income category.
-
B.
reducedTopMarginalRateTo
Indicates that an entity has lowered the highest marginal rate (such as a top tax or interest rate) to a specified new level.
-
C.
reducedTopMarginalRateFrom
Indicates that an entity lowered the highest marginal rate (such as a top tax or interest rate) from a specified prior level.
-
D.
topIndividualRateAfterReform
chosen
Indicates the highest individual rate that applies following the implementation of a reform.
-
E.
topCorporateRateAfterReform
Indicates the highest corporate tax rate that applies following the implementation of a specified tax reform.
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f185121da0819095b523d7d2c923ab |
completed | April 29, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:53 p.m.