Triple
T23513728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Direct Unsubsidized Loan |
E572500
|
entity |
| Predicate | accruesInterestFrom |
P97196
|
FINISHED |
| Object | date of first disbursement |
—
|
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: date of first disbursement | Statement: [Direct Unsubsidized Loan, accruesInterestFrom, date of first disbursement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accruesInterestFrom Context triple: [Direct Unsubsidized Loan, accruesInterestFrom, date of first disbursement]
-
A.
accrualFrom
chosen
Indicates that something (such as a benefit, cost, or amount) arises, accumulates, or is derived from a specified source or cause.
-
B.
accrualUnit
Indicates the unit of measure (such as days, months, or years) in which something accumulates or is accrued over time.
-
C.
maximumAccrualPeriod
Indicates the longest time span over which something (such as interest, benefits, or rights) can accumulate before it stops accruing.
-
D.
accrualMethod
Indicates the method or basis by which something (such as interest, revenue, or benefits) is accumulated or recognized over time.
-
E.
interestCharged
Indicates that a specified amount of interest is imposed on a principal or outstanding balance over a given 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_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.