Triple

T20863489
Position Surface form Disambiguated ID Type / Status
Subject How to Murder Your Wife E513684 entity
Predicate mainCharacter P1183 FINISHED
Object Mrs. Ford 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: Mrs. Ford | Statement: [How to Murder Your Wife, mainCharacter, Mrs. Ford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mrs. Ford
Context triple: [How to Murder Your Wife, mainCharacter, Mrs. Ford]
  • A. Mrs. Ford chosen
    Mrs. Ford is a clever, resourceful married woman who helps orchestrate the comic humiliation of Falstaff in Verdi’s opera "Falstaff."
  • B. Dorothy Ford
    Dorothy Ford is the grandmother of Georgia Ford, known primarily through her familial connection within the Ford family.
  • C. Lena Guilbert Ford
    Lena Guilbert Ford was an American lyricist best known for writing the words to the popular World War I song "Keep the Home Fires Burning."
  • D. Mrs Richards
    Mrs Richards is a hard-of-hearing, cantankerous guest character from the classic British sitcom Fawlty Towers, known for her argumentative interactions with Basil Fawlty.
  • E. Elizabeth Smith
    Elizabeth Smith was the mother of George Monck, the 1st Duke of Albemarle, a key military figure in the English Restoration.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c45d2ec4819098abbb901b9fcd87 completed April 21, 2026, 12:27 a.m.
Created at: April 16, 2026, 12:44 p.m.