Triple

T1805975
Position Surface form Disambiguated ID Type / Status
Subject Behind the Candelabra E40219 entity
Predicate editor P1954 FINISHED
Object Mary Ann Bernard
Mary Ann Bernard is a film editor best known for her work on the biographical drama "Behind the Candelabra."
E285665 NE FINISHED

How this triple was built (4 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: Mary Ann Bernard | Statement: [Behind the Candelabra, editor, Mary Ann Bernard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Ann Bernard
Context triple: [Behind the Candelabra, editor, Mary Ann Bernard]
  • A. Mary Ann Bertles
    Mary Ann Bertles was the wife of U.S. Supreme Court Justice Potter Stewart.
  • B. Mary Ann Holmes
    Mary Ann Holmes was the mother of renowned 19th-century American actor Edwin Booth and the wife of Shakespearean tragedian Junius Brutus Booth.
  • C. Mary Anne Grindall
    Mary Anne Grindall was the wife of British civil servant, political reformer, and ornithologist Allan Octavian Hume.
  • D. Mary Easty
    Mary Easty was a respected Salem, Massachusetts woman who was falsely accused of witchcraft and executed during the 1692 Salem witch trials, later remembered for her dignified plea for justice.
  • E. Mary Elizabeth Ellis
    Mary Elizabeth Ellis is an American actress and comedian best known for her recurring role as The Waitress on the TV series "It's Always Sunny in Philadelphia."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary Ann Bernard
Triple: [Behind the Candelabra, editor, Mary Ann Bernard]
Generated description
Mary Ann Bernard is a film editor best known for her work on the biographical drama "Behind the Candelabra."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Ann Bernard
Target entity description: Mary Ann Bernard is a film editor best known for her work on the biographical drama "Behind the Candelabra."
  • A. Mary Ann Bertles
    Mary Ann Bertles was the wife of U.S. Supreme Court Justice Potter Stewart.
  • B. Mary Ann Holmes
    Mary Ann Holmes was the mother of renowned 19th-century American actor Edwin Booth and the wife of Shakespearean tragedian Junius Brutus Booth.
  • C. Mary Anne Grindall
    Mary Anne Grindall was the wife of British civil servant, political reformer, and ornithologist Allan Octavian Hume.
  • D. Mary Easty
    Mary Easty was a respected Salem, Massachusetts woman who was falsely accused of witchcraft and executed during the 1692 Salem witch trials, later remembered for her dignified plea for justice.
  • E. Mary Elizabeth Ellis
    Mary Elizabeth Ellis is an American actress and comedian best known for her recurring role as The Waitress on the TV series "It's Always Sunny in Philadelphia."
  • F. None of above. chosen

Provenance (5 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_69a88643a3388190a612f2ebe1fb29e7 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa659798b88190bd3070349ce6bebb completed March 6, 2026, 5:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69af989789308190bb124c2c1706b68c completed March 10, 2026, 4:05 a.m.
NEDg Description generation batch_69af99416924819099d4acb1a2d60e0c completed March 10, 2026, 4:08 a.m.
NED2 Entity disambiguation (via description) batch_69af99adadb08190a44f2286b25bf0aa completed March 10, 2026, 4:10 a.m.
Created at: March 4, 2026, 7:32 p.m.