Triple

T23018049
Position Surface form Disambiguated ID Type / Status
Subject Pursuit to Algiers E573085 entity
Predicate screenwriter P2831 FINISHED
Object Leonard Lee 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: Leonard Lee | Statement: [Pursuit to Algiers, screenwriter, Leonard Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leonard Lee
Context triple: [Pursuit to Algiers, screenwriter, Leonard Lee]
  • A. Leonard Lee chosen
    Leonard Lee is a screenwriter known for his work on the film "The Maze."
  • B. Leonard Leroy Lee
    Leonard Leroy Lee is the birth name of American actor Robert Fuller, known for his roles in classic Western television series such as "Laramie" and "Wagon Train."
  • C. Leonard Smith
    Leonard Smith was an American cinematographer best known for his work on classic Hollywood films, including the Technicolor family drama "National Velvet."
  • D. Leonard Robinson
    Leonard Robinson is the brother of American fashion designer and businesswoman Tory Burch.
  • E. Leonard Gordon
    Leonard Gordon was a cardiologist and manager best known as the longtime husband of acclaimed actress and EGOT-winning performer Rita Moreno.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.