Triple

T17815656
Position Surface form Disambiguated ID Type / Status
Subject Karl Ferris E444831 entity
Predicate name P16 FINISHED
Object Karl Ferris 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: Karl Ferris | Statement: [Karl Ferris, name, Karl Ferris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl Ferris
Context triple: [Karl Ferris, name, Karl Ferris]
  • A. Karl Ferris chosen
    Karl Ferris is a British photographer best known for his pioneering psychedelic imagery on 1960s rock album covers, particularly for Jimi Hendrix.
  • B. Karl Burns
    Karl Burns was an English drummer best known for his multiple stints with the influential post-punk band The Fall, where his inventive and sometimes volatile presence became part of the group’s legend.
  • C. Karl VanDevender
    Karl VanDevender is an American physician best known as the husband of acclaimed novelist Ann Patchett.
  • D. Bob Ferris
    Bob Ferris is the central, working-class everyman character from the British television sitcoms "The Likely Lads" and "Whatever Happened to the Likely Lads?".
  • E. Karl Dane
    Karl Dane was a Danish-American silent film actor best known for his comic roles in 1920s Hollywood, particularly as part of the popular screen duo "Dane & Arthur."
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4887f7d048190b6d813b9f0fab3e7 completed April 19, 2026, 7:47 a.m.
Created at: April 10, 2026, 10:14 a.m.