Triple
T23041833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Dot Corporation |
E573756
|
entity |
| Predicate | hasBankSubsidiaryType |
P38626
|
FINISHED |
| Object | online bank |
—
|
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: online bank | Statement: [Green Dot Corporation, hasBankSubsidiaryType, online bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBankSubsidiaryType Context triple: [Green Dot Corporation, hasBankSubsidiaryType, online bank]
-
A.
hasBankType
Indicates that an entity is associated with or classified by a particular type or category of bank.
-
B.
hasSubsidiaryLabel
Indicates that one entity is identified as a subsidiary or subordinate organization of another entity.
-
C.
hasSubsidiaryBusiness
Indicates that one business entity owns or controls another business entity as its subsidiary.
-
D.
hasSubOrganizationType
chosen
Indicates that an organization is associated with or classified under a specific type or category of sub-organization.
-
E.
hasSubsidiaryTop
Indicates that one organization is the primary or top-level parent of another organization that operates as its subsidiary.
- 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_69e245b9c11481909d06c872214d21af |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18513fc54819096d761a0be75b774 |
completed | April 29, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:54 p.m.