Triple
T36261227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illinois 529 college savings plans |
E892091
|
entity |
| Predicate | taxTreatmentFederal |
P126136
|
FINISHED |
| Object | earnings grow tax-deferred |
—
|
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: earnings grow tax-deferred | Statement: [Illinois 529 college savings plans, taxTreatmentFederal, earnings grow tax-deferred]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taxTreatmentFederal Context triple: [Illinois 529 college savings plans, taxTreatmentFederal, earnings grow tax-deferred]
-
A.
taxType
Indicates the specific category or classification of tax that applies to an entity, transaction, or amount.
-
B.
taxCharacteristic
Indicates the specific tax-related property, status, or classification that applies to an entity or transaction.
-
C.
taxTreatmentOfEarnings
chosen
Indicates how earnings are classified and handled for tax purposes within a given financial or legal context.
-
D.
taxationMethod
Indicates the specific way or system by which taxes are calculated, collected, or applied in a given context.
-
E.
taxFunction
Indicates the rule or calculation method used to determine the amount of tax applied to a given input (such as income, price, 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_69f76e4699188190af045b11a840ce31 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b6227808819085a3d728329481a0 |
completed | May 3, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c44390819084fb5558b354658f |
completed | May 3, 2026, 8:49 p.m. |
Created at: May 3, 2026, 4:09 p.m.