Triple

T17065766
Position Surface form Disambiguated ID Type / Status
Subject Billie Frechette E414082 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is the given first name of Billie Frechette, the Native American woman known for her association with bank robber John Dillinger during the early 1930s.
E1248799 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: [Billie Frechette, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Billie Frechette, givenName, Mary]
  • A. Mary
    Mary is a fictional character in B.F. Skinner’s utopian novel "Walden Two," representing one of the community’s young members shaped by its behaviorist social principles.
  • B. Mary
    Mary is the middle name of Edith Tolkien, the wife of author J.R.R. Tolkien.
  • C. 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.
  • 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 a film featuring Italian actor Marco Leonardi, known for his roles in internationally acclaimed 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: [Billie Frechette, givenName, Mary]
Generated description
Mary is the given first name of Billie Frechette, the Native American woman known for her association with bank robber John Dillinger during the early 1930s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is the given first name of Billie Frechette, the Native American woman known for her association with bank robber John Dillinger during the early 1930s.
  • A. Mary
    Mary is the given first name of American actress, author, and radio host Marilu Henner.
  • B. Mary
    Mary is the given name of Mary Church Terrell, a prominent African American civil rights activist, educator, and suffragist in the late 19th and early 20th centuries.
  • C. Mary
    Mary is the given name of Mary Woronov, an American actress, author, and underground film icon associated with Andy Warhol’s Factory scene.
  • D. Mary
    Mary is the given name of American character actress Marjorie Main, known for her roles in classic Hollywood films.
  • E. Mary
    Mary is the given name of Mary Ludwig Hays, an American Revolutionary War figure often associated with the legendary heroine "Molly Pitcher."
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3db8171348190ab68d2e4f05f7120 completed April 18, 2026, 7:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01234e9a94819094618ba43b7d22b4 completed May 11, 2026, 12:31 a.m.
NEDg Description generation batch_6a01245aa7ec81909fa20befa29f590c completed May 11, 2026, 12:35 a.m.
NED2 Entity disambiguation (via description) batch_6a01281c8bf08190a24d77fe6af595f4 completed May 11, 2026, 12:51 a.m.
Created at: April 10, 2026, 5:34 a.m.