Triple

T9098377
Position Surface form Disambiguated ID Type / Status
Subject Jean Adair E218086 entity
Predicate name P16 FINISHED
Object Jean Adair E218086 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 Adair | Statement: [Jean Adair, name, Jean Adair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Adair
Context triple: [Jean Adair, name, Jean Adair]
  • A. Jean Adair chosen
    Jean Adair was a Canadian-born American character actress best known for originating and later reprising on film the role of one of the eccentric Brewster sisters in "Arsenic and Old Lace."
  • B. Jane Holt
    Jane Holt was the wife of prominent 18th-century Presbyterian minister and educator Samuel Davies.
  • C. Mary Campbell
    Mary Campbell is a central character in the satirical television sitcom "Soap," known for her role in the show's parody of daytime soap opera tropes.
  • D. Helen Ferguson
    Helen Ferguson was an American silent film actress prominent in the 1910s and 1920s who later became a successful Hollywood publicist.
  • E. Helen Ferguson
    Helen Ferguson is a secondary character in Ernest Hemingway's novel "A Farewell to Arms," serving as Catherine Barkley's protective friend and a skeptical observer of her relationship with Frederic Henry.
  • 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_69ca83d9844081908e561e367fda6d45 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc970f340881909f5551219f151acf completed April 1, 2026, 3:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69d01824ee2081909cc5e6ae33fab2e5 completed April 3, 2026, 7:42 p.m.
Created at: March 30, 2026, 7:15 p.m.