Triple
T6245763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Family Education Loan Program |
E139716
|
entity |
| Predicate | guaranteeAgencyInvolved |
P32141
|
FINISHED |
| Object | state guaranty agencies |
—
|
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: state guaranty agencies | Statement: [Federal Family Education Loan Program, guaranteeAgencyInvolved, state guaranty agencies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guaranteeAgencyInvolved Context triple: [Federal Family Education Loan Program, guaranteeAgencyInvolved, state guaranty agencies]
-
A.
affectedAgency
Indicates that one entity has an effect on, or causes a change in, the agency or capacity for action of another entity.
-
B.
involvedAgreement
Indicates that an entity participates in, is a party to, or is otherwise associated with a specific agreement or contract.
-
C.
guaranteeProvider
chosen
Indicates that one entity serves as the party that provides or issues a guarantee for another entity or obligation.
-
D.
respondingAgency
Indicates which agency or organization takes action or provides the primary response in relation to a given event, request, or incident.
-
E.
constantInvolved
Indicates that a constant participates in or is directly involved in the specified relation, operation, or context.
- 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_69c008b1c5088190ae6de2555fc05ad8 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0631d9e648190a59ab4001f506424 |
completed | March 22, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69c056037bf88190a0a3fe7429345d0b |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:23 p.m.