Triple
T21532194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnold Clark |
E531256
|
entity |
| Predicate | hasRetailSitesIn |
P26597
|
FINISHED |
| Object | major UK cities |
—
|
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: major UK cities | Statement: [Arnold Clark, hasRetailSitesIn, major UK cities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetailSitesIn Context triple: [Arnold Clark, hasRetailSitesIn, major UK cities]
-
A.
hasRetailPresenceIn
chosen
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.
hasRetailBoutiquesIn
Indicates that an entity operates or maintains retail boutiques located within a specified place or region.
-
D.
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.
-
E.
hasRetailMarkets
Indicates that an entity operates, hosts, or is associated with one or more retail markets where goods or services are sold to consumers.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0a0e7c8190bbb7ed5c4dfe33af |
completed | April 26, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:27 p.m.