Triple
T16320070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mint Julep |
E396266
|
entity |
| Predicate | drinkingStraw |
P42717
|
FINISHED |
| Object | often served with short straw |
—
|
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: often served with short straw | Statement: [Mint Julep, drinkingStraw, often served with short straw]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drinkingStraw Context triple: [Mint Julep, drinkingStraw, often served with short straw]
-
A.
stillOrSparkling
Indicates whether something, typically a beverage, is non-carbonated (still) or carbonated (sparkling).
-
B.
stickType
chosen
Indicates the specific kind or category of stick associated with or used in relation to an entity.
-
C.
drinks
Indicates that one entity consumes a liquid substance, typically by ingesting it through the mouth.
-
D.
containsJuice
Indicates that one entity has juice inside it or as one of its contents.
-
E.
bottlingMaterial
Indicates the material from which a container or bottle used for holding a product is made.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b4ad448190b2b195a5e0032c6e |
completed | April 17, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69e219fc72c881909d452274e7af8238 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.