Triple

T11773823
Position Surface form Disambiguated ID Type / Status
Subject Novocaine E279965 entity
Predicate character P662 FINISHED
Object Jean Noble E335679 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: Jean Noble | Statement: [Novocaine, character, Jean Noble]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Noble
Context triple: [Novocaine, character, Jean Noble]
  • A. Patricia Dainton chosen
    Patricia Dainton was a British film and television actress known for her roles in 1950s and 1960s thrillers and dramas.
  • B. Catherine Aldrich
    Catherine Aldrich is an individual associated with the use of something identified by the name Aldrich, though specific public biographical or professional details about her are not widely documented.
  • C. Ruth Myers
    Ruth Myers is an acclaimed British costume designer known for her imaginative and character-defining work on numerous films and television productions.
  • D. Amy Lindley
    Amy Lindley is a fictional character from the television series "Dawson's Creek," known as the daughter of Jen Lindley.
  • E. Catherine Wells
    Catherine Wells is known as the wife of Canadian actor Henry Czerny, recognized for his roles in film and television such as the Mission: Impossible series.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a55dfa088190a59b35d0247225e3 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f68e9b70d08190aa74e612947317b5 completed May 2, 2026, 11:54 p.m.
Created at: April 8, 2026, 9:41 p.m.