Triple

T3971239
Position Surface form Disambiguated ID Type / Status
Subject Murder on the Orient Express E92339 entity
Predicate mainCharacter P1183 FINISHED
Object Hercule Poirot E246267 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: Hercule Poirot | Statement: [Murder on the Orient Express, mainCharacter, Hercule Poirot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hercule Poirot
Context triple: [Murder on the Orient Express, mainCharacter, Hercule Poirot]
  • A. Hercule Poirot chosen
    Hercule Poirot is Agatha Christie's famously fastidious Belgian detective known for his brilliant deductive reasoning and reliance on his "little grey cells" to solve complex mysteries.
  • B. Hugh Sherlock
    Hugh Sherlock was a Jamaican clergyman, social worker, and poet best known for writing the lyrics of Jamaica’s national anthem.
  • C. Dr. Watson
    Dr. Watson is the loyal friend, assistant, and biographer of Sherlock Holmes in Arthur Conan Doyle’s detective stories.
  • D. Cornelius Sherlock
    Cornelius Sherlock was a British architect best known for designing prominent public buildings such as the Walker Art Gallery in Liverpool.
  • E. Arthur Ibbetson
    Arthur Ibbetson was a British cinematographer known for his work on notable films such as "The Bounty," "Anne of the Thousand Days," and "Willy Wonka & the Chocolate Factory."
  • 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_69aed96624188190ac8c45bb57ab72b5 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef995d27881908b24a5b2ef57455f completed March 9, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5400b75d081909b8e4840b15d19f1 completed March 14, 2026, 11:01 a.m.
Created at: March 9, 2026, 3:32 p.m.