Triple

T19719984
Position Surface form Disambiguated ID Type / Status
Subject Dale Eunson E473580 entity
Predicate child P120 FINISHED
Object Joan Evans 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: Joan Evans | Statement: [Dale Eunson, child, Joan Evans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Evans
Context triple: [Dale Eunson, child, Joan Evans]
  • A. Joan Evans chosen
    Joan Evans was an American film actress active in the 1940s and 1950s, known for her roles in Hollywood dramas and coming-of-age films.
  • B. Joan Tompkins
    Joan Tompkins was an American character actress known for her work in mid-20th-century film and television.
  • C. Joan Goushill
    Joan Goushill was an English noblewoman of the late medieval period, notable as the mother of Thomas Stanley, 1st Earl of Derby, and for her connections to prominent aristocratic families.
  • D. Joan Fulton
    Joan Fulton is the birth name of American character actress Joan Shawlee, known for her comedic supporting roles in mid-20th-century films and television.
  • E. Joan Hinton
    Joan Hinton was an American nuclear physicist who worked on the Manhattan Project and later became known for her pro-communist activism and decades-long life in China as a critic of U.S. nuclear policy.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e64410e5548190b60e13603b6c0053 completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.