Triple
T23123084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graduate PLUS Loan |
E576952
|
entity |
| Predicate | interestAccrues |
P19983
|
FINISHED |
| Object | while in school |
—
|
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: while in school | Statement: [Graduate PLUS Loan, interestAccrues, while in school]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interestAccrues Context triple: [Graduate PLUS Loan, interestAccrues, while in school]
-
A.
interestCharged
chosen
Indicates that a specified amount of interest is imposed on a principal or outstanding balance over a given period.
-
B.
interestRateDetermination
Indicates the relationship by which the applicable interest rate is set, defined, or adjusted for a financial obligation or instrument.
-
C.
balancesInterest
Indicates that an entity manages or adjusts multiple interests or priorities so that none is disproportionately favored over the others.
-
D.
effectOnTotalInterest
Indicates how a given factor or action changes the overall amount of interest accrued or owed.
-
E.
insuranceAccrualRate
Indicates the rate at which insurance-related amounts (such as premiums, costs, or liabilities) accumulate over a specified period.
- 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e517a0481909829a73fdf255d1c |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.