Triple

T2920241
Position Surface form Disambiguated ID Type / Status
Subject Moffat Toffee E78701 entity
Predicate hasKeyCharacteristic P274 FINISHED
Object boiled sweet with tangy centre 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: boiled sweet with tangy centre | Statement: [Moffat Toffee, hasKeyCharacteristic, boiled sweet with tangy centre]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasKeyCharacteristic
Context triple: [Moffat Toffee, hasKeyCharacteristic, boiled sweet with tangy centre]
  • A. hasCharacteristic chosen
    Indicates that an entity possesses, exhibits, or is defined by a particular attribute, feature, or quality.
  • B. hasKeyCapability
    Indicates that an entity possesses an essential ability or function that is critical for performing a particular task or role.
  • C. hasKeyFigure
    Indicates that an entity includes, involves, or is characterized by an important or central person relevant to it.
  • D. hasKeyActivity
    Indicates that an entity is associated with or performs a primary or central activity.
  • E. hasKeyImage
    Indicates that one entity is designated as the primary or representative image associated with another entity.
  • 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad97fd89d88190bc7db4b39058ae3a completed March 8, 2026, 3:38 p.m.
PD Predicate disambiguation batch_69ad9603ddd88190b8bf91bc7517cc21 completed March 8, 2026, 3:30 p.m.
Created at: March 8, 2026, 2:54 p.m.