Triple
T6110074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mellon tax cuts of the 1920s |
E136213
|
entity |
| Predicate | topMarginalRateBeforeReform |
P37500
|
FINISHED |
| Object | 73 percent |
—
|
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: 73 percent | Statement: [Mellon tax cuts of the 1920s, topMarginalRateBeforeReform, 73 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topMarginalRateBeforeReform Context triple: [Mellon tax cuts of the 1920s, topMarginalRateBeforeReform, 73 percent]
-
A.
topCorporateRateBeforeReform
Indicates the highest corporate tax rate that was in effect prior to a specified tax reform or policy change.
-
B.
topIndividualRateBeforeReform
chosen
Indicates the highest individual rate that applied prior to a specified reform or policy change.
-
C.
topIndividualRateAfterReform
Indicates the highest individual rate that applies following the implementation of a reform.
-
D.
topCorporateRateAfterReform
Indicates the highest corporate tax rate that applies following the implementation of a specified tax reform.
-
E.
inflationRateBefore
Indicates that one inflation rate occurred earlier in time than another inflation rate being considered.
- 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_69c0089ea6f88190b349be53e04b4f5f |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b84ed088190a12cdb844d743326 |
completed | March 22, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69c049f80e2081909b7d84a104cda68d |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:13 p.m.