Triple
T6293708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbecue Capital of the World |
E141079
|
entity |
| Predicate | hasTypicalSauce |
P51950
|
FINISHED |
| Object | vinegar-based barbecue sauce |
—
|
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: vinegar-based barbecue sauce | Statement: [Barbecue Capital of the World, hasTypicalSauce, vinegar-based barbecue sauce]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalSauce Context triple: [Barbecue Capital of the World, hasTypicalSauce, vinegar-based barbecue sauce]
-
A.
sauceType
chosen
Indicates the specific kind or category of sauce associated with an item or dish.
-
B.
typicalSauceConsistency
Indicates that something has the usual or characteristic thickness or texture expected of a sauce.
-
C.
isTypicallyGarnishedWith
Indicates that one item is commonly used as a garnish or decorative finishing element for another.
-
D.
hasGravy
Indicates that one entity is accompanied by, covered with, or served with gravy in relation to another entity or context.
-
E.
hasMainIngredient
Indicates that one entity is the primary or most significant ingredient used to make another entity.
- 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06438654481908c9833c5f0d61773 |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:27 p.m.