Triple
T23513784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Perkins Loan |
E572501
|
entity |
| Predicate | subsidized |
P123933
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Federal Perkins Loan, subsidized, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subsidized Context triple: [Federal Perkins Loan, subsidized, true]
-
A.
subsidizedInterest
Indicates that the interest on a loan or financial obligation is partially or fully paid or reduced by a third party, typically a government or institution, rather than borne entirely by the borrower.
-
B.
wasStateSubsidized
chosen
Indicates that an entity received financial support or subsidies from a state or government authority.
-
C.
typeOfSubsidy
Indicates that one entity is a specific kind or category of subsidy in relation to another entity.
-
D.
subsidyAttachment
Indicates that a subsidy is linked or applied to a particular entity, object, or transaction.
-
E.
compensated
Indicates that one entity provides payment or some form of recompense to another entity in return for goods, services, or loss incurred.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa80174c819088c9c19fdcf2a133 |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:08 p.m.