Triple
T7869692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Home Loan Bank Act |
E182706
|
entity |
| Predicate | targetInstitutions |
P67775
|
FINISHED |
| Object | thrift institutions |
—
|
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: thrift institutions | Statement: [Federal Home Loan Bank Act, targetInstitutions, thrift institutions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetInstitutions Context triple: [Federal Home Loan Bank Act, targetInstitutions, thrift institutions]
-
A.
targetOrganizations
chosen
Indicates the organizations that are the intended recipients or focus of an action, initiative, or influence.
-
B.
numberOfTargetInstitutions
Indicates the count of institutions that are designated or identified as targets in a given context or dataset.
-
C.
hasInstitutions
Indicates that one entity possesses, contains, or is associated with one or more institutions.
-
D.
centralInstitutionOf
Indicates that one institution serves as the primary or main institutional center for another entity, such as an organization, system, or region.
-
E.
targetOrganization
Indicates that one entity is the organization that is the focus, recipient, or primary subject of another entity’s action, service, or relationship.
- 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_69ca82894d9081908a832bfce71a4714 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3848d6d88190830afcf04ad12154 |
completed | March 31, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69cae925ca388190ae4a01fa76e957e8 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:55 p.m.