Triple

T15768805
Position Surface form Disambiguated ID Type / Status
Subject Twister E382294 entity
Predicate starring P1507 FINISHED
Object Lois Smith E274922 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: Lois Smith | Statement: [Twister, starring, Lois Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lois Smith
Context triple: [Twister, starring, Lois Smith]
  • A. Lois Smith chosen
    Lois Smith is an American character actress known for her nuanced performances in film, television, and theater over a career spanning several decades.
  • B. Phyllis Thaxter
    Phyllis Thaxter was an American film, television, and stage actress best known for her roles in mid-20th-century Hollywood dramas and for playing Martha Kent in the 1978 film "Superman."
  • C. Glynis Johns
    Glynis Johns was a British actress and singer known for her distinctive husky voice and roles in films such as "Mary Poppins" and "The Court Jester," as well as her work on stage and television.
  • D. Linda Harrison
    Linda Harrison is an American actress best known for her role as Nova in the original "Planet of the Apes" films.
  • E. Phyllis Kirk
    Phyllis Kirk was an American actress best known for her roles in 1950s film noir and horror, including the classic 3D film "House of Wax."
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0084a6d6308190ad57a51b380171a2 completed May 10, 2026, 1:14 p.m.
Created at: April 10, 2026, 4:47 a.m.