Triple

T12531382
Position Surface form Disambiguated ID Type / Status
Subject The Salisbury Poisonings E299570 entity
Predicate stars P1956 FINISHED
Object Johnny Harris E994561 NE FINISHED

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: Johnny Harris | Statement: [The Salisbury Poisonings, stars, Johnny Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnny Harris
Context triple: [The Salisbury Poisonings, stars, Johnny Harris]
  • A. Johnny Harris chosen
    Johnny Harris is a British actor known for his intense, gritty performances in film and television dramas.
  • B. Billy Harris
    Billy Harris is a British actor best known for his role as footballer Colin Hughes in the television series "Ted Lasso."
  • C. Jimmy Frizzell
    Jimmy Frizzell was a Scottish football manager and former player best known for his long and influential spell in charge of Oldham Athletic during the 1970s and early 1980s.
  • D. Gene Harris
    Gene Harris was an American jazz pianist celebrated for his soulful, blues-infused style and influential work in both small groups and big band settings.
  • E. Bill Anderson
    Bill Anderson is one of the three possible fathers and a central figure in the musical and film "Mamma Mia!", known for his adventurous, easygoing personality and past romance with Donna.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95469d100819087c83bc55e3ec9ce completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6718cd6288190ad080f469f334caf completed May 2, 2026, 9:50 p.m.
Created at: April 8, 2026, 9:57 p.m.