Triple
T19709768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nationwide Building Society |
E473310
|
entity |
| Predicate | followsBusinessModel |
P74458
|
FINISHED |
| Object | member-owned |
—
|
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: member-owned | Statement: [Nationwide Building Society, followsBusinessModel, member-owned]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsBusinessModel Context triple: [Nationwide Building Society, followsBusinessModel, member-owned]
-
A.
usesBusinessModel
Indicates that one entity operates according to, or applies in practice, the business model defined or provided by another entity.
-
B.
laterBusinessModel
Indicates that one business model occurs or is adopted after another in time, representing a subsequent or successor business model in a sequence.
-
C.
businessModelElement
Indicates that one entity functions as a component or element within the overall business model of another entity.
-
D.
businessModelType
chosen
Indicates the type or category of business model that characterizes how an entity creates, delivers, and captures value.
-
E.
hasBusinessModelCharacteristic
Indicates that a business model possesses or exhibits a specific feature, quality, or attribute.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e64406f9808190acd74aa03c392eb0 |
completed | April 20, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:46 p.m.