Triple
T99798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chase Manhattan Bank |
E2015
|
entity |
| Predicate | servedClientType |
P809
|
FINISHED |
| Object | retail customers |
—
|
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 customers | Statement: [Chase Manhattan Bank, servedClientType, retail customers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedClientType Context triple: [Chase Manhattan Bank, servedClientType, retail customers]
-
A.
servedByService
Indicates that something is provided, handled, or fulfilled by a particular service.
-
B.
customerType
chosen
Indicates the classification or category assigned to a customer based on their characteristics, status, or relationship with a business.
-
C.
hasServiceType
Indicates that an entity is associated with or categorized by a particular type of service.
-
D.
sessionType
Indicates the classification or category of a particular session based on its purpose, format, or context.
-
E.
hasVisitorType
Indicates the type or category of visitor associated with an entity (e.g., guest, customer, tourist, patient).
- 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_69a24d4862f881908cc8b89d3a78031d |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a253b95d4c81909d1f2bc37e799c44 |
completed | Feb. 28, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69a24ebfc5a88190bdd1653b9fa541fe |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:09 a.m.