Triple

T14751229
Position Surface form Disambiguated ID Type / Status
Subject Scott Fuller E346610 entity
Predicate fictionalSibling P34570 FINISHED
Object Kate Fuller 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: Kate Fuller | Statement: [Scott Fuller, fictionalSibling, Kate Fuller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Fuller
Context triple: [Scott Fuller, fictionalSibling, Kate Fuller]
  • A. Kate Fuller chosen
    Kate Fuller is a central protagonist in the "From Dusk Till Dawn" franchise, portrayed as a resilient young woman who survives a violent encounter with criminals and vampires.
  • B. Ann Fuller
    Ann Fuller is known as the wife of American film director, screenwriter, and novelist Samuel Fuller.
  • C. Jane Fuller
    Jane Fuller is a central character in the science fiction film "The Thirteenth Floor," involved in the story’s layered virtual-reality conspiracy.
  • D. Elizabeth Griscom
    Elizabeth Griscom, better known as Betsy Ross, was an American upholsterer and seamstress traditionally credited with sewing the first flag of the United States.
  • E. Mary Fuller
    Mary Fuller was a popular American silent film actress of the 1910s, best known for her work in early motion pictures produced by Edison Studios.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7d40efc8190bb1be34c19a2b57c completed April 14, 2026, 11:03 p.m.
Created at: April 10, 2026, 1:30 a.m.