Triple
T11187710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metro by T-Mobile |
E264715
|
entity |
| Predicate | hasRetailPresence |
P87312
|
FINISHED |
| Object | company-owned stores |
—
|
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: company-owned stores | Statement: [Metro by T-Mobile, hasRetailPresence, company-owned stores]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetailPresence Context triple: [Metro by T-Mobile, hasRetailPresence, company-owned stores]
-
A.
hasRetailPresenceIn
Indicates that an entity conducts retail operations or maintains a retail outlet, store, or sales presence within a specified location.
-
B.
hasRetailStores
chosen
Indicates that an entity operates or possesses one or more physical retail store locations.
-
C.
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.
-
D.
hasRetailBoutiquesIn
Indicates that an entity operates or maintains retail boutiques located within a specified place or region.
-
E.
hasRetailFormat
Indicates that one entity operates or is organized according to a particular retail format or store type.
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8ad143481908d5dacc95837ecfd |
completed | April 9, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69d75cf4461c8190af84060f7db83211 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.