Triple

T22760522
Position Surface form Disambiguated ID Type / Status
Subject Mister Johnson E562974 entity
Predicate title P38 FINISHED
Object Mister Johnson 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: Mister Johnson | Statement: [Mister Johnson, title, Mister Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mister Johnson
Context triple: [Mister Johnson, title, Mister Johnson]
  • A. Mister Johnson chosen
    Mister Johnson is a 1990 drama film directed by Bruce Beresford, adapted from Joyce Cary’s novel about a Nigerian clerk navigating British colonial rule in the 1920s.
  • B. Mr. Johnson
    Mr. Johnson is a fictional character who appears in the work titled "The Psychiatrist."
  • C. Mr. Bryles
    Mr. Bryles is the central character in the 1999-set story "Class of 1999," around whom the main events and conflicts revolve.
  • D. Mr. Peebles
    Mr. Peebles is the pet shop owner in the classic Hanna-Barbera cartoon "Magilla Gorilla," known for repeatedly trying to sell the lovable gorilla Magilla.
  • E. Mr. Robinson
    Mr. Robinson is the father of Elaine Robinson, a central character in the story of "The Graduate."
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a7c45b881908b29ba1439038789 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:26 p.m.