Triple

T18147452
Position Surface form Disambiguated ID Type / Status
Subject Angie Bowie E434424 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is the birth name of Angie Bowie, the American model, actress, and former wife of musician David Bowie.
E1308196 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 | Statement: [Angie Bowie, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Angie Bowie, givenName, Mary]
  • A. Mary
    Mary is the given name of Mary Jo Kopechne, the American political campaign specialist who died in the 1969 Chappaquiddick incident involving Senator Ted Kennedy.
  • B. Mary
    Mary is the middle name of Edith Tolkien, the wife of author J.R.R. Tolkien.
  • C. Mary
    Mary is the central protagonist of the play "The Memory of Water," around whom the story’s emotional and familial conflicts revolve.
  • D. Mary
    Mary is the birth name of American actress, comedian, and writer Lily Tomlin, known for her groundbreaking work in television, film, and theater.
  • E. Mary
    Mary is the given name of the American stage and film actress Josephine Hull, known for her roles in classic mid-20th-century theater and cinema.
  • 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
Triple: [Angie Bowie, givenName, Mary]
Generated description
Mary is the birth name of Angie Bowie, the American model, actress, and former wife of musician David Bowie.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is the birth name of Angie Bowie, the American model, actress, and former wife of musician David Bowie.
  • A. Mary
    Mary is the given name of Mary J. Blige, the acclaimed American singer, songwriter, and actress often called the "Queen of Hip-Hop Soul."
  • B. Mary
    Mary is the birth name of American model and actress Lauren Hutton, a pioneering figure in fashion known for her gap-toothed smile and influential modeling career.
  • C. Mary
    Mary is the birth name of Australian actress Rose Byrne, known for her roles in films like "Bridesmaids" and the "X-Men" series.
  • D. Mary
    Mary is the birth name of American actress Sean Young, known for her roles in films such as "Blade Runner" and "Dune."
  • E. Mary
    Mary is the birth name of American actress, singer, and dancer Debbie Reynolds, a major Hollywood star of the mid-20th century.
  • 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_69d8b90aac308190801e2c57d8c5bfe5 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4de34bb608190a4842e86f2912dec completed April 19, 2026, 1:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03855631f48190ae8c343a4fa8f2a6 completed May 12, 2026, 7:53 p.m.
NEDg Description generation batch_6a0385d8a43c8190b61222b65c1f9a60 completed May 12, 2026, 7:56 p.m.
NED2 Entity disambiguation (via description) batch_6a03868a4898819083dc64e9d39b6c80 completed May 12, 2026, 7:59 p.m.
Created at: April 10, 2026, 10:29 a.m.