Triple
T1808114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 7(a) Loan Program |
E40266
|
entity |
| Predicate | guaranteeCoverage |
P32142
|
FINISHED |
| Object | portion of loan principal rather than full amount |
—
|
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: portion of loan principal rather than full amount | Statement: [7(a) Loan Program, guaranteeCoverage, portion of loan principal rather than full amount]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guaranteeCoverage Context triple: [7(a) Loan Program, guaranteeCoverage, portion of loan principal rather than full amount]
-
A.
hasCoverage
Indicates that one entity provides insurance or protection coverage for another entity or subject.
-
B.
primaryCoverage
Indicates that one entity serves as the main or principal source of coverage (such as insurance or protection) for another entity.
-
C.
typeOfDiscriminationCovered
Indicates that a particular kind or category of discriminatory behavior is included within the scope of protections, rules, or analysis.
-
D.
isCoveredBy
Indicates that one entity is physically or conceptually overlaid, protected, or enclosed by another entity.
-
E.
alsoCovers
Indicates that something extends its scope or applicability to include an additional subject, area, or case beyond what was originally covered.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69ab694bf6a08190a02ce2fc979e6701 |
completed | March 6, 2026, 11:54 p.m. |
Created at: March 4, 2026, 7:32 p.m.