Triple

T18100977
Position Surface form Disambiguated ID Type / Status
Subject Thomas Davison printing business E433213 entity
Predicate operatedBy P86 FINISHED
Object Thomas Davison 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: Thomas Davison | Statement: [Thomas Davison printing business, operatedBy, Thomas Davison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Davison
Context triple: [Thomas Davison printing business, operatedBy, Thomas Davison]
  • A. Thomas Davison chosen
    Thomas Davison was a 19th-century British printer and publisher best known for issuing the first edition of Lord Byron’s poem "Don Juan."
  • B. John Tordoff
    John Tordoff is a British actor known for his work in film, television, and theatre, including a role in the 1987 adaptation of "The Magic Toyshop."
  • C. Sir Ronald Davison
    Sir Ronald Davison was a prominent New Zealand jurist who served as Chief Justice and played a key role in the country’s legal system in the late 20th century.
  • D. John Thomas Duckworth
    John Thomas Duckworth was a British Royal Navy admiral noted for his leadership and victories during the Napoleonic Wars.
  • E. Tito Davison
    Tito Davison was a Mexican film director and screenwriter known for his work in Latin American cinema from the 1930s through the 1960s.
  • 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddb5e6208190b3c3cce3b95d66ad completed April 19, 2026, 1:50 p.m.
Created at: April 10, 2026, 10:27 a.m.