Triple
T27769386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swiss Bank Corporation |
E701698
|
entity |
| Predicate | hadClientele |
P163231
|
FINISHED |
| Object | institutional investors |
—
|
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: institutional investors | Statement: [Swiss Bank Corporation, hadClientele, institutional investors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadClientele Context triple: [Swiss Bank Corporation, hadClientele, institutional investors]
-
A.
hadClientele
chosen
Indicates that an entity regularly served or catered to a particular group of clients or customers.
-
B.
hadCustom
Indicates that an entity previously possessed or was associated with a customized or user-defined version of something.
-
C.
hasCustomers
Indicates that an entity maintains a business relationship in which other entities purchase or receive its goods or services as customers.
-
D.
hadMember
Indicates that an entity was formerly a member or part of another entity or group.
-
E.
hadCommon
Indicates that two or more entities shared the same attribute, experience, or element in common.
- 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_69ef6a52fa708190934a32308d2c92dc |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63894e5848190aec428392562ab06 |
completed | May 2, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 4:33 p.m.