Triple

T7024896
Position Surface form Disambiguated ID Type / Status
Subject I Married a Witch E162918 entity
Predicate screenwriter P2831 FINISHED
Object Marc Connelly E236321 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: Marc Connelly | Statement: [I Married a Witch, screenwriter, Marc Connelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc Connelly
Context triple: [I Married a Witch, screenwriter, Marc Connelly]
  • A. Marc Connelly chosen
    Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
  • B. Andy Connell
    Andy Connell is an English musician and composer best known as a member of the jazz-pop duo Swing Out Sister and for his earlier work in the post-punk and new wave scenes.
  • C. Joe Connolly
    Joe Connolly was a Major League Baseball outfielder best known for his role on the 1914 "Miracle" Boston Braves championship team.
  • D. Christian O'Connell
    Christian O'Connell is a British radio DJ, comedian, and author best known for hosting popular breakfast shows in the UK and Australia.
  • E. Kevin Connor
    Kevin Connor is a film editor known for his work on the satirical World War I musical film "Oh! What a Lovely War."
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79c80aae08190a388db9110fdebdf completed March 28, 2026, 9:16 a.m.
Created at: March 27, 2026, 2:35 p.m.