Triple

T32647052
Position Surface form Disambiguated ID Type / Status
Subject Duke Weaselton E834622 entity
Predicate metaReferenceTo P170315 FINISHED
Object Duke of Weselton from Frozen NE NERFINISHED

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: Duke of Weselton from Frozen | Statement: [Duke Weaselton, metaReferenceTo, Duke of Weselton from Frozen]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: metaReferenceTo
Context triple: [Duke Weaselton, metaReferenceTo, Duke of Weselton from Frozen]
  • A. metaReferenceOf chosen
    Indicates that one entity serves as a meta-level reference or description of another entity, rather than being the primary object itself.
  • B. alsoRefersTo
    Indicates that one term, label, or identifier is used as an alternative designation for the same entity or concept as another.
  • C. referenceSectionFor
    Indicates a relationship where one resource serves as the reference section or reference material specifically associated with another resource.
  • D. crossReference
    Indicates that one entity refers the user to another related entity or source for additional or supporting information.
  • E. notablyRefersTo
    Indicates that one entity makes a particularly significant or noteworthy reference to another entity, beyond a routine or incidental mention.
  • 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_69f3492e773c81908afc10651e46cad3 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69f6c775d6188190b236fc4f89a11b61 completed May 3, 2026, 3:56 a.m.
PD Predicate disambiguation batch_69f6c3f617c08190a70ba880210f908c completed May 3, 2026, 3:41 a.m.
Created at: May 1, 2026, 1:07 a.m.