Triple
T1891719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ale & Compass Restaurant |
E41887
|
entity |
| Predicate | servesBeverage |
P9634
|
FINISHED |
| Object | cocktails |
—
|
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: cocktails | Statement: [Ale & Compass Restaurant, servesBeverage, cocktails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesBeverage Context triple: [Ale & Compass Restaurant, servesBeverage, cocktails]
-
A.
featuresBeverage
Indicates that one entity includes, offers, or presents a particular beverage as part of its contents, services, or characteristics.
-
B.
stateBeverage
Indicates that an entity is a beverage associated with or designated by a particular state or region.
-
C.
canServeIn
Indicates that one entity is eligible, authorized, or suitable to perform a role, function, or duty within another entity, context, or organization.
-
D.
servesAlcohol
chosen
Indicates that an establishment or provider offers and supplies alcoholic beverages to customers or participants.
-
E.
servesOn
Indicates that one entity performs duties, functions, or holds a role as a member within another entity, such as a group, body, or organization.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb145f96c8190a71bb9e442892e68 |
completed | March 7, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69abafe61bc48190ac9ead027df930e1 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.