Triple
T23123071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PLUS Loan |
E576951
|
entity |
| Predicate | excessFundsRefundedTo |
P150996
|
FINISHED |
| Object | borrower or student, depending on authorization |
—
|
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: borrower or student, depending on authorization | Statement: [PLUS Loan, excessFundsRefundedTo, borrower or student, depending on authorization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: excessFundsRefundedTo Context triple: [PLUS Loan, excessFundsRefundedTo, borrower or student, depending on authorization]
-
A.
usedFund
Indicates that one entity expended or applied a particular fund or financial resource for some purpose.
-
B.
refundForm
Indicates that an entity is a form or process used to request or process a refund for another entity.
-
C.
refundablePortionName
Indicates the specific name or label assigned to the portion of an amount that is eligible to be refunded.
-
D.
refundabilityType
Indicates the specific conditions or category under which something (typically a payment, ticket, or product) can be refunded.
-
E.
refundable
Indicates that an item, service, or payment can be returned or canceled in exchange for a reimbursement of money.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69ef9b7494f4819088ae59ea3d0ae8ab |
completed | April 27, 2026, 5:23 p.m. |
Created at: April 17, 2026, 3:59 p.m.