Triple
T7669791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comerica Bank |
E173717
|
entity |
| Predicate | FDICInsured |
P40552
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Comerica Bank, FDICInsured, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FDICInsured Context triple: [Comerica Bank, FDICInsured, true]
-
A.
isFDICInsured
chosen
Indicates that a financial institution or account is covered by insurance from the Federal Deposit Insurance Corporation (FDIC), protecting deposits up to the insured limits.
-
B.
typeOfDepositInsurance
Indicates the specific kind or category of deposit insurance that applies to a financial account or institution.
-
C.
insuredInstitutionType
Indicates the type or category of institution that is covered under an insurance arrangement or policy.
-
D.
commonDeposits
Indicates that two or more entities share the same or overlapping deposit locations or accounts.
-
E.
hasFinancialInstitution
Indicates that one entity is associated with or linked to a financial institution, such as a bank or similar financial service provider.
- 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_69c699562484819086752091e3164a27 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7063dab1881909598b04999b8b690 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015f7430819099d3ea2781b7cee2 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 4 p.m.