Triple
T23513882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Income-Contingent Repayment Plan (ICR) |
E572503
|
entity |
| Predicate | paymentFormula |
P25081
|
FINISHED |
| Object | 20 percent of discretionary income |
—
|
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: 20 percent of discretionary income | Statement: [Income-Contingent Repayment Plan (ICR), paymentFormula, 20 percent of discretionary income]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paymentFormula Context triple: [Income-Contingent Repayment Plan (ICR), paymentFormula, 20 percent of discretionary income]
-
A.
paymentStructure
chosen
Indicates how payments are organized, scheduled, and divided between the involved parties.
-
B.
paymentAmount
Indicates the specific monetary value involved in a payment transaction between parties.
-
C.
interestPaymentMethod
Indicates the method or mechanism by which interest is paid in the context of a financial relationship or agreement.
-
D.
payReform
Indicates a relationship where an authority changes or restructures the pay system, such as salaries or compensation terms, for a group of people.
-
E.
closingFormula
Indicates the conventional closing phrase or formula used to end a communication, such as a letter, email, or message.
- 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.