Triple
T1808102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 7(a) Loan Program |
E40266
|
entity |
| Predicate | maximumLoanAmount |
P29667
|
FINISHED |
| Object | typically up to $5 million |
—
|
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: typically up to $5 million | Statement: [7(a) Loan Program, maximumLoanAmount, typically up to $5 million]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumLoanAmount Context triple: [7(a) Loan Program, maximumLoanAmount, typically up to $5 million]
-
A.
loanLimitType
Indicates the category or rule that defines how a loan’s maximum allowable amount or terms are limited.
-
B.
collateralRequired
Indicates that a party must provide collateral as a condition or security for an obligation, transaction, or agreement.
-
C.
loanType
Indicates the specific category or kind of loan associated with an entity or transaction.
-
D.
maximumNumber
chosen
Indicates that one entity specifies the highest allowable or observed quantity, value, or count associated with another entity.
-
E.
eligibleBorrower
Indicates that an entity meets the required conditions to be allowed to borrow (e.g., money, items, or resources) under a given set of rules or policies.
- 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab694d75ac8190a4d61399c04b9fb9 |
completed | March 6, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69aa61d6b8ec8190a1597b2e44ea6534 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.