Triple
T451564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starbucks |
E7139
|
entity |
| Predicate | hasStoreFormat |
P4952
|
FINISHED |
| Object | standalone 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: standalone stores | Statement: [Starbucks, hasStoreFormat, standalone stores]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStoreFormat Context triple: [Starbucks, hasStoreFormat, standalone stores]
-
A.
hasRetailFormat
chosen
Indicates that one entity operates or is organized according to a particular retail format or store type.
-
B.
hasFileFormat
Indicates that one entity (typically a digital file or resource) is encoded, stored, or represented using a specific file format defined by the other entity.
-
C.
hasExhibitFormat
Indicates the specific format or medium in which an exhibit is presented or made available.
-
D.
hasNonStandardForm
Indicates that an entity possesses a form, variant, or representation that deviates from the standard, canonical, or commonly accepted form.
-
E.
hasPublishingFormat
Indicates that an entity is associated with a specific format or medium in which it is published or made publicly available.
- 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_69a2e7e4676c81909ea0dbdecac0687c |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ef835ae881908884dcc3a46af951 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede3187c8190a7ced078f0ec3476 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.