Triple

T19178672
Position Surface form Disambiguated ID Type / Status
Subject The Last Trump E469511 entity
Predicate hasFictionalStoryteller P68311 FINISHED
Object Harry Purvis 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: Harry Purvis | Statement: [The Last Trump, hasFictionalStoryteller, Harry Purvis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Purvis
Context triple: [The Last Trump, hasFictionalStoryteller, Harry Purvis]
  • A. Harry Purvis chosen
    Harry Purvis is the witty, often unreliable raconteur who narrates the tall, science-fictional barroom stories in Arthur C. Clarke’s collection "Tales from the White Hart."
  • B. Jack Purvis
    Jack Purvis was a British dwarf actor best known for his roles in several Terry Gilliam films and the original Star Wars trilogy.
  • C. Henry Sherwin
    Henry Sherwin was an American businessman best known as the co-founder of the Sherwin-Williams Company, a major paint and coatings manufacturer.
  • D. Reginald Purdell
    Reginald Purdell was a British character actor and occasional screenwriter known for his supporting roles in numerous films from the 1930s and 1940s.
  • E. Philip Hudson
    Philip Hudson was an Australian architect best known for co-designing Melbourne’s iconic Shrine of Remembrance war memorial.
  • 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_69d8dd09d5a081909ae43c286651ae5a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f619c60c81909d11489525add829 completed April 20, 2026, 9:47 a.m.
Created at: April 10, 2026, 12:07 p.m.