Triple
T23104249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subsidized Federal Stafford Loan |
E576117
|
entity |
| Predicate | defermentOptions |
P42633
|
FINISHED |
| Object | in-school deferment |
—
|
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: in-school deferment | Statement: [Subsidized Federal Stafford Loan, defermentOptions, in-school deferment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defermentOptions Context triple: [Subsidized Federal Stafford Loan, defermentOptions, in-school deferment]
-
A.
canDelayMoneyBillsFor
Indicates that one entity has the authority or ability to postpone or extend the payment deadline of money-related bills for another entity.
-
B.
repaymentPlanEligibility
Indicates whether an entity qualifies to enter into or maintain a specified repayment plan under defined rules or criteria.
-
C.
mayDelay
chosen
Indicates that one entity has the potential or permission to cause a postponement or slowing of another entity, event, or process.
-
D.
disbursementOption
Indicates the method or arrangement by which funds are paid out or distributed.
-
E.
dismissalModes
Indicates the ways or conditions under which something (such as a case, request, or entity) can be dismissed, closed, or removed.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18deb702c819099f2e2141706f00e |
completed | April 29, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:58 p.m.