Triple
T19223406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makro (UK) |
E480674
|
entity |
| Predicate | hasCompetitor |
P1375
|
FINISHED |
| Object | Bestway Wholesale |
—
|
NE NERFINISHED |
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: Bestway Wholesale | Statement: [Makro (UK), hasCompetitor, Bestway Wholesale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bestway Wholesale Context triple: [Makro (UK), hasCompetitor, Bestway Wholesale]
-
A.
Daisy Outdoor Products
Daisy Outdoor Products is an American manufacturer best known for its iconic BB guns and air rifles, including the famous Red Ryder model.
-
B.
Bondway
Bondway is a street in the Vauxhall area of London, located near Vauxhall Station and forming part of the surrounding road network.
-
C.
Booker Wholesale
chosen
Booker Wholesale is a major UK cash-and-carry and foodservice wholesaler supplying retailers, caterers, and small businesses with a wide range of grocery and related products.
-
D.
Weider
Weider is a surname most prominently associated with Joe Weider, a pioneering figure in bodybuilding and fitness publishing.
-
E.
Amway
Amway is a global multi-level marketing company that sells health, beauty, and home care products through a network of independent distributors.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa95743481909314fd14e2c3d189 |
completed | April 20, 2026, 10:06 a.m. |
Created at: April 10, 2026, 1:24 p.m.