Triple
T1804741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Trains |
E39794
|
entity |
| Predicate | servedCustomerType |
P19115
|
FINISHED |
| Object | commuters |
—
|
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: commuters | Statement: [Virgin Trains, servedCustomerType, commuters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedCustomerType Context triple: [Virgin Trains, servedCustomerType, commuters]
-
A.
customerType
Indicates the classification or category assigned to a customer based on their characteristics, status, or relationship with a business.
-
B.
categoryOfPeopleServed
chosen
Indicates the type or group of people that are the primary recipients or beneficiaries of a service or activity.
-
C.
servesCustomer
Indicates that one entity provides service, assistance, or products to another entity in the role of a customer.
-
D.
notableServiceType
Indicates that the subject is associated with a particular type or category of service that is especially notable or significant.
-
E.
siteTypeServed
Indicates the type of site or location that is served, supported, or handled by a given entity or resource.
- 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_69a88632aa588190ba3978fde0db5bbd |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aba67721788190951beae25e885457 |
completed | March 7, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69aa61d514c081908197ac1f7c7d7a88 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.