Triple
T11357657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBNA America |
E269001
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | MBNA |
E269001
|
NE 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: MBNA | Statement: [MBNA America, brand, MBNA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MBNA Context triple: [MBNA America, brand, MBNA]
-
A.
MBNA America
chosen
MBNA America was a major U.S. bank holding company and one of the largest issuers of credit cards before its acquisition by Bank of America.
-
B.
MBNA UK
MBNA UK is a British credit card provider that operates as a subsidiary of Lloyds Banking Group.
-
C.
Discover Card
Discover Card is a major U.S. credit card brand known for its cash-back rewards, no annual fees on many cards, and widespread acceptance.
-
D.
American Express
American Express is a global financial services company best known for its charge and credit cards, payment network, and travel-related services.
-
E.
Mastercard
Mastercard is a global financial services corporation best known for its widely used credit and debit card payment network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea419afc8190b3a93141d015ebdf |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e556542ecc8190a8109c17944598ab |
completed | April 19, 2026, 10:25 p.m. |
Created at: April 8, 2026, 9:33 p.m.