Triple
T18702757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SAN |
E457291
|
entity |
| Predicate | issuerMainBusiness |
P105459
|
FINISHED |
| Object | retail banking |
—
|
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: retail banking | Statement: [SAN, issuerMainBusiness, retail banking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: issuerMainBusiness Context triple: [SAN, issuerMainBusiness, retail banking]
-
A.
issuerOriginalBusiness
Indicates that an entity is the original business organization that issued or created another entity (such as a document, instrument, or product).
-
B.
issuerBusinessType
chosen
Indicates the category or nature of business activity that the issuing entity is engaged in.
-
C.
issuerMainPlatform
Indicates that an entity serves as the primary platform or main environment through which an issuer operates, offers, or manages its services or instruments.
-
D.
issuerOwnsBusinessesIn
Indicates that the issuer owns one or more business entities that are located or operate within the specified place.
-
E.
issuerBestKnownFor
Indicates the primary work, achievement, or characteristic for which an issuer is most widely recognized.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56714d0588190ac050356bc2784fd |
completed | April 19, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69e478de85088190ba5f005f1d39f587 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:49 a.m.