Triple

T23026003
Position Surface form Disambiguated ID Type / Status
Subject Blanche Oelrichs E573314 entity
Predicate spouse P13 FINISHED
Object John Barrymore 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: John Barrymore | Statement: [Blanche Oelrichs, spouse, John Barrymore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Barrymore
Context triple: [Blanche Oelrichs, spouse, John Barrymore]
  • A. John Barrymore chosen
    John Barrymore was a renowned American stage and film actor of the early 20th century, celebrated for his Shakespearean roles and charismatic screen presence.
  • B. Lionel Barrymore
    Lionel Barrymore was an American actor and director best known for his prolific film career in the early 20th century, including his iconic role as Mr. Potter in "It's a Wonderful Life."
  • C. Warren William
    Warren William was an American stage and film actor of the 1930s, best known for his suave, often morally ambiguous leading and supporting roles in Hollywood pre-Code dramas and mysteries.
  • D. Zasu Pitts
    Zasu Pitts was an American actress best known for her distinctive comedic persona in early Hollywood films and later in radio and television.
  • E. Charles Ruggles
    Charles Ruggles was an American character actor known for his comedic roles in film, radio, and television from the 1920s through the 1960s.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1847d7cb48190902169813c46a278 completed April 29, 2026, 4:09 a.m.
Created at: April 17, 2026, 3:52 p.m.