Triple
T13463979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belvoir Castle café |
E311445
|
entity |
| Predicate | typicalMenuItems |
P93917
|
FINISHED |
| Object | hot drinks |
—
|
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: hot drinks | Statement: [Belvoir Castle café, typicalMenuItems, hot drinks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMenuItems Context triple: [Belvoir Castle café, typicalMenuItems, hot drinks]
-
A.
menuType
Indicates the classification or category of a menu (e.g., main menu, context menu, settings menu) associated with an interface or system.
-
B.
menuItemType
chosen
Indicates the relationship between a menu item and the type or category it belongs to (e.g., appetizer, main course, dessert).
-
C.
typicalItem
Indicates that an item is a representative or characteristic example of a broader category, class, or set.
-
D.
typicalOrder
Indicates the usual or most common sequence or arrangement in which related elements, events, or components occur.
-
E.
typicalCommands
Indicates that the associated entity commonly issues or uses the specified commands as part of its normal or expected behavior.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf0f1830819085700b4521e44678 |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69dbadfddefc81909ef7fde23b181b5c |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:41 p.m.