Triple

T20898022
Position Surface form Disambiguated ID Type / Status
Subject The Worst Witch E514593 entity
Predicate publisher P29 FINISHED
Object Allison & Busby — NE NERFINISHED

How this triple was built (3 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: Allison & Busby | Statement: [The Worst Witch, publisher, Allison & Busby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Allison & Busby
Context triple: [The Worst Witch, publisher, Allison & Busby]
  • A. Nelson & Murdock
    Nelson & Murdock is a small New York City law firm in Marvel Comics, best known as the practice run by Matt Murdock (Daredevil) and his partner Foggy Nelson.
  • B. Lundy & Frank
    Lundy & Frank was an American architectural firm known for designing prominent federal buildings, including the U.S. Tax Court Building in Washington, D.C.
  • C. McDonald & Dodds
    McDonald & Dodds is a British crime drama television series that follows the unlikely partnership between a shrewd but socially awkward detective and his ambitious boss as they solve complex cases in the city of Bath.
  • D. Nichols and May
    Nichols and May was a groundbreaking American comedy duo of Mike Nichols and Elaine May, celebrated for their sharp, sophisticated improvisational sketches in the late 1950s and early 1960s.
  • E. Githens & Keally
    Githens & Keally was an American architectural firm best known for its prominent public and institutional buildings in the early to mid-20th century.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Allison & Busby
Target entity description: Allison & Busby is an independent British publishing house known for releasing a range of fiction and non-fiction titles, including popular children’s books.
  • A. Nelson & Murdock
    Nelson & Murdock is a small New York City law firm in Marvel Comics, best known as the practice run by Matt Murdock (Daredevil) and his partner Foggy Nelson.
  • B. Lundy & Frank
    Lundy & Frank was an American architectural firm known for designing prominent federal buildings, including the U.S. Tax Court Building in Washington, D.C.
  • C. McDonald & Dodds
    McDonald & Dodds is a British crime drama television series that follows the unlikely partnership between a shrewd but socially awkward detective and his ambitious boss as they solve complex cases in the city of Bath.
  • D. Nichols and May
    Nichols and May was a groundbreaking American comedy duo of Mike Nichols and Elaine May, celebrated for their sharp, sophisticated improvisational sketches in the late 1950s and early 1960s.
  • E. Githens & Keally
    Githens & Keally was an American architectural firm best known for its prominent public and institutional buildings in the early to mid-20th century.
  • F. None of above. chosen

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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8f826788190b11008cc94b2a4e4 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.