Triple
T23018617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TEACH Grant Program |
E573102
|
entity |
| Predicate | conversionLoanType |
P9377
|
FINISHED |
| Object | Direct Unsubsidized Loan |
—
|
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: Direct Unsubsidized Loan | Statement: [TEACH Grant Program, conversionLoanType, Direct Unsubsidized Loan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conversionLoanType Context triple: [TEACH Grant Program, conversionLoanType, Direct Unsubsidized Loan]
-
A.
loanType
chosen
Indicates the specific category or kind of loan associated with an entity or transaction.
-
B.
conversionTarget
Indicates that one entity serves as the intended outcome, goal, or result that another entity is meant to be converted or transformed into.
-
C.
conversionBasis
Indicates the reference standard, rate, or unit system used as the foundation for converting one quantity, unit, or representation into another.
-
D.
conversionProgram
Indicates a program or process that transforms something from one form, state, or type into another.
-
E.
conversionOfferedIn
Indicates that an opportunity to convert (e.g., change status, format, or type) is made available within or through a specified context, channel, or environment.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:52 p.m.