Triple

T23193853
Position Surface form Disambiguated ID Type / Status
Subject FFELP E579820 entity
Predicate guarantyAgencyRole P32141 FINISHED
Object insure lenders against borrower default 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: insure lenders against borrower default | Statement: [FFELP, guarantyAgencyRole, insure lenders against borrower default]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: guarantyAgencyRole
Context triple: [FFELP, guarantyAgencyRole, insure lenders against borrower default]
  • A. guaranteeProvider chosen
    Indicates that one entity serves as the party that provides or issues a guarantee for another entity or obligation.
  • B. roleInCollateral
    Indicates that an entity participates in or is assigned a specific role within a collateral arrangement or structure.
  • C. servesAgency
    Indicates that one entity performs services or functions on behalf of, or under the authority of, an agency.
  • D. definesAsPermanentAgency
    Indicates that one entity formally establishes another entity as a permanent agency or enduring representative body, rather than a temporary or ad hoc arrangement.
  • E. designatesAgencyAs
    Indicates that one entity formally assigns or recognizes another entity as its acting agency or representative body.
  • 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_69e24600eed08190bd7e5295653a1503 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18fd971d08190a132d24094e0c37b completed April 29, 2026, 4:58 a.m.
PD Predicate disambiguation batch_69ef8a041c0081909afb670d17a5aaba completed April 27, 2026, 4:08 p.m.
Created at: April 17, 2026, 4:06 p.m.