Triple
T14376619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carphone Warehouse |
E356490
|
entity |
| Predicate | hasRetailOutletType |
P4952
|
FINISHED |
| Object | high-street store |
—
|
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: high-street store | Statement: [Carphone Warehouse, hasRetailOutletType, high-street store]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetailOutletType Context triple: [Carphone Warehouse, hasRetailOutletType, high-street store]
-
A.
hasRetailPresenceIn
Indicates that an entity conducts retail operations or maintains a retail outlet, store, or sales presence within a specified location.
-
B.
hasRetailStores
Indicates that an entity operates or possesses one or more physical retail store locations.
-
C.
hasRetailFormat
chosen
Indicates that one entity operates or is organized according to a particular retail format or store type.
-
D.
hasOutletStores
Indicates that an entity operates or is associated with one or more outlet retail stores.
-
E.
hasRetailNetwork
Indicates that an entity operates or is associated with a system of retail outlets or distribution channels through which products or services are sold.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69de2a9cb3e081909f6b33fdd939bb9e |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:16 a.m.