Triple
T16320068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mint Julep |
E396266
|
entity |
| Predicate | servingVesselMaterial |
P94570
|
FINISHED |
| Object | silver cup |
—
|
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: silver cup | Statement: [Mint Julep, servingVesselMaterial, silver cup]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servingVesselMaterial Context triple: [Mint Julep, servingVesselMaterial, silver cup]
-
A.
servingVessel
Indicates that one entity functions as the container or vessel used to serve another entity (such as food or drink).
-
B.
tableware
chosen
Indicates that an entity is a piece of tableware (such as dishes, utensils, or related items) used in serving or consuming food and drink.
-
C.
dishType
Indicates the classification of a dish according to its culinary category or role (e.g., appetizer, main course, dessert).
-
D.
dishShape
Indicates that one entity has the physical form or contour characterized by the other entity as its shape.
-
E.
possibleFermentationVessel
Indicates that something can serve as a suitable container or environment in which fermentation may take place.
- 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.