Triple

T9112478
Position Surface form Disambiguated ID Type / Status
Subject Inspector Lestrade E218635 entity
Predicate fictionalUniverse P3758 FINISHED
Object Sherlock Holmes E5614 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: Sherlock Holmes | Statement: [Inspector Lestrade, fictionalUniverse, Sherlock Holmes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sherlock Holmes
Context triple: [Inspector Lestrade, fictionalUniverse, Sherlock Holmes]
  • A. Hugh Sherlock
    Hugh Sherlock was a Jamaican clergyman, social worker, and poet best known for writing the lyrics of Jamaica’s national anthem.
  • B. Jerry Sherlock
    Jerry Sherlock was a film producer best known for producing the 1990 submarine thriller "The Hunt for Red October."
  • C. Holmes chosen
    Holmes is a common English surname borne by numerous notable figures, including writers, jurists, and fictional characters such as Sherlock Holmes.
  • D. Holmes
    Holmes is a consumer brand best known for its home comfort products such as fans, heaters, and air purifiers.
  • E. Dr. Watson
    Dr. Watson is the loyal friend, assistant, and biographer of Sherlock Holmes in Arthur Conan Doyle’s detective stories.
  • 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_69ca83dc94ac8190b9ef42684d36ff39 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8495c448190b9bb3803fb2dda70 completed April 1, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05bf002c081909bb82bb765bbf4b1 completed April 4, 2026, 12:31 a.m.
Created at: March 30, 2026, 7:16 p.m.