Triple

T14162696
Position Surface form Disambiguated ID Type / Status
Subject Mary (1978 TV series) E350987 entity
Predicate hasTitle P38 FINISHED
Object Mary
Mary is a 1978 American television series starring Mary Tyler Moore in a short-lived variety show format following her earlier sitcom success.
E354283 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: [Mary (1978 TV series), hasTitle, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Mary (1978 TV series), hasTitle, Mary]
  • A. Mary
    Mary is the given name of the American suspense novelist Mary Higgins Clark, known for her bestselling mystery and thriller books.
  • B. Mary
    Mary is the given name of Mary Catherine Bateson, an American cultural anthropologist and writer known for her work on learning and the human life cycle.
  • C. Mary
    Mary of Lancaster was a 14th-century English noblewoman, daughter of Henry, 3rd Earl of Lancaster, and a member of the influential House of Lancaster.
  • D. Mary
    Mary is the middle name of Joseph Plunkett, the Irish nationalist, poet, and 1916 Easter Rising leader.
  • E. Mary
    Mary is the birth name of American actress, comedian, and writer Lily Tomlin, known for her groundbreaking work in television, film, and theater.
  • 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: [Mary (1978 TV series), hasTitle, Mary]
Generated description
Mary is a 1978 American television series starring Mary Tyler Moore in a short-lived variety show format following her earlier sitcom success.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is a 1978 American television series starring Mary Tyler Moore in a short-lived variety show format following her earlier sitcom success.
  • A. Mary chosen
    Mary is the given name of American actress and television icon Mary Tyler Moore, best known for her roles in "The Dick Van Dyke Show" and "The Mary Tyler Moore Show."
  • B. Mary
    Mary is the birth name of American actress, comedian, and writer Lily Tomlin, known for her groundbreaking work in television, film, and theater.
  • C. Mary
    Mary is the given first name of American actress Marg Helgenberger, known for her role on the television series "CSI: Crime Scene Investigation."
  • D. Mary
    Mary is the given name of American actress, singer, director, and screenwriter Mary Kay Place, known for her work in film and television since the 1970s.
  • E. Mary
    Mary is the given first name of American actress, author, and radio host Marilu Henner.
  • F. None of above.

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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de613a4a2081908fd51bf4b4d82b6c completed April 14, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7f3170481909f3981c1e56235d9 completed May 7, 2026, 8:37 p.m.
NEDg Description generation batch_69fcfe9debe08190b9943f941f1b8813 completed May 7, 2026, 9:05 p.m.
NED2 Entity disambiguation (via description) batch_69fcff29f7608190b4b7d24fc1e011bf completed May 7, 2026, 9:07 p.m.
Created at: April 10, 2026, 12:59 a.m.