Triple
T36977561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taxpayer Relief Act of 1997 |
E914740
|
entity |
| Predicate | expandedDeduction |
P5633
|
FINISHED |
| Object | student loan interest deduction |
—
|
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: student loan interest deduction | Statement: [Taxpayer Relief Act of 1997, expandedDeduction, student loan interest deduction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expandedDeduction Context triple: [Taxpayer Relief Act of 1997, expandedDeduction, student loan interest deduction]
-
A.
expandedBy
chosen
Indicates that one entity increases, elaborates, or builds upon the scope, detail, or extent of another entity.
-
B.
expandedAs
Indicates that one entity is a more detailed, elaborated, or fully written-out form of another, capturing how the latter is expanded from the former.
-
C.
taxDeductible
Indicates that an expense, contribution, or item is eligible to be subtracted from taxable income under applicable tax rules.
-
D.
expandable
Indicates that something can be increased, extended, or enlarged in size, scope, or capacity beyond its current state.
-
E.
restrictedExpansionOf
Indicates a relationship where one entity is an expansion of another, but with added constraints or limitations that make it more specific or narrowly applicable than the original.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb6fdc7eb081908ab8475efb38c430 |
completed | May 6, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69fb5a986e588190b7a10892bd2ff44c |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:14 p.m.