Triple

T21416323
Position Surface form Disambiguated ID Type / Status
Subject Angel (1937 film) E528305 entity
Predicate screenwriter P2831 FINISHED
Object Frederick Lonsdale 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: Frederick Lonsdale | Statement: [Angel (1937 film), screenwriter, Frederick Lonsdale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frederick Lonsdale
Context triple: [Angel (1937 film), screenwriter, Frederick Lonsdale]
  • A. Frederick Lonsdale chosen
    Frederick Lonsdale was a British playwright and screenwriter best known for his sophisticated comedies of manners and popular stage successes in the early 20th century.
  • B. Peter Lonsdale
    Peter Lonsdale is a film editor known for his work on the animated feature "Shark Tale."
  • C. Frederick Birks
    Frederick Birks was an Australian soldier and recipient of the Victoria Cross for his bravery during World War I.
  • D. Harry Lonsdale
    Harry Lonsdale was an early 20th-century actor known for his roles in silent films.
  • E. John Bowes Morrell
    John Bowes Morrell was a prominent English historian, author, and civic leader from York who played a key role in the founding and development of the University of York.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b205d17c8190b9b6b5708658f9be completed April 22, 2026, 11:33 a.m.
Created at: April 16, 2026, 5:46 p.m.