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.