Triple

T11624760
Position Surface form Disambiguated ID Type / Status
Subject John Henry Brodribb E276235 entity
Predicate birthName P65 FINISHED
Object John Henry Brodribb E276235 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: John Henry Brodribb | Statement: [John Henry Brodribb, birthName, John Henry Brodribb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Henry Brodribb
Context triple: [John Henry Brodribb, birthName, John Henry Brodribb]
  • A. John Henry Brodribb chosen
    John Henry Brodribb, better known as Sir Henry Irving, was a renowned 19th-century English stage actor and the first actor to be knighted.
  • B. William Brinkley
    William Brinkley was an American novelist and journalist best known for his satirical World War II naval novel "Don't Go Near the Water" and the post-apocalyptic submarine thriller "The Last Ship."
  • C. William Cottrell
    William Cottrell was an American screenwriter and director best known for his work on classic Disney animated films in the mid-20th century.
  • D. William Scudder
    William Scudder is a person notable enough to be specifically recorded as a bearer of the surname Scudder.
  • E. John Bunnell
    John Bunnell is a former American sheriff and television personality best known for hosting and narrating dramatic law-enforcement reality shows.
  • 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_69d6aafa51148190ab84940694c00235 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a12416908190ac2dcd7f7ebb308f completed April 10, 2026, 7:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69f457dc01ec8190a7ee3108d4d95957 completed May 1, 2026, 7:35 a.m.
Created at: April 8, 2026, 9:39 p.m.