Triple
T824033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PayPal Working Capital |
E17812
|
entity |
| Predicate | repaymentBasis |
P6447
|
FINISHED |
| Object | percentage of daily PayPal sales |
—
|
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: percentage of daily PayPal sales | Statement: [PayPal Working Capital, repaymentBasis, percentage of daily PayPal sales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repaymentBasis Context triple: [PayPal Working Capital, repaymentBasis, percentage of daily PayPal sales]
-
A.
repaymentTrigger
Indicates that a specific event or condition causes a repayment obligation to become due or activated.
-
B.
calculationBasis
chosen
Indicates the rule, method, or reference standard used as the foundation for performing a calculation in the relationship.
-
C.
creditSchedule
Indicates a planned or agreed-upon timetable for extending, using, or repaying credit between parties.
-
D.
debtFullyRepaidYear
Indicates the specific year in which a debt obligation has been completely repaid.
-
E.
returnBasis
Indicates the basis, method, or terms under which something is returned (e.g., goods, funds, or data) from one party or context to another.
- 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_69a4937c9c188190aaa216f6b466f452 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ab7d3984819089aefbf12d3b3c2c |
completed | March 1, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69a4aa781e1081909df006f730296c53 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.