Triple
T11057588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chasselas wine |
E261417
|
entity |
| Predicate | servingGlassType |
P72115
|
FINISHED |
| Object | white wine glass |
—
|
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: white wine glass | Statement: [Chasselas wine, servingGlassType, white wine glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servingGlassType Context triple: [Chasselas wine, servingGlassType, white wine glass]
-
A.
servingVessel
chosen
Indicates that one entity functions as the container or vessel used to serve another entity (such as food or drink).
-
B.
typeOfCup
Indicates the specific kind or category of cup that an entity is associated with or classified as.
-
C.
sparklingType
Indicates that one entity is classified as a specific type or category within the broader class of sparkling items or phenomena.
-
D.
servesType
Indicates that one entity provides, offers, or is used to deliver a particular type, category, or kind of thing or service.
-
E.
alcoholType
Indicates the specific kind or category of alcohol associated with an entity (e.g., beer, wine, spirits).
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798a2efa48190b290f43dfe836501 |
completed | April 9, 2026, 12:16 p.m. |
| PD | Predicate disambiguation | batch_69d7440da46c8190a77380d5d747ac9c |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.