Triple

T18347865
Position Surface form Disambiguated ID Type / Status
Subject Jerome Y. Lettvin E439588 entity
Predicate spouse P13 FINISHED
Object Maggie Lettvin
Maggie Lettvin is an American health and fitness educator best known for her influential 1970s public television exercise programs and books.
E1319449 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: Maggie Lettvin | Statement: [Jerome Y. Lettvin, spouse, Maggie Lettvin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maggie Lettvin
Context triple: [Jerome Y. Lettvin, spouse, Maggie Lettvin]
  • A. Margaret Rudman
    Margaret Rudman is known as the wife of the late U.S. Senator Warren Rudman of New Hampshire.
  • B. Margaret Rudkin
    Margaret Rudkin was an American businesswoman and food industry pioneer best known for building Pepperidge Farm from a home baking venture into a major commercial bakery brand.
  • C. Patricia Bloomfield
    Patricia Bloomfield is known as the wife of renowned Dutch conductor Bernard Haitink.
  • D. Frances Neagley
    Frances Neagley is a highly skilled, fiercely loyal former U.S. Army MP and close ally of Jack Reacher who frequently assists him in investigations throughout Lee Child’s thriller series.
  • E. Gillian Siddall
    Gillian Siddall is a Canadian academic and university administrator who serves as president of Lakehead University.
  • 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: Maggie Lettvin
Triple: [Jerome Y. Lettvin, spouse, Maggie Lettvin]
Generated description
Maggie Lettvin is an American health and fitness educator best known for her influential 1970s public television exercise programs and books.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maggie Lettvin
Target entity description: Maggie Lettvin is an American health and fitness educator best known for her influential 1970s public television exercise programs and books.
  • A. Margaret Rudman
    Margaret Rudman is known as the wife of the late U.S. Senator Warren Rudman of New Hampshire.
  • B. Margaret Rudkin
    Margaret Rudkin was an American businesswoman and food industry pioneer best known for building Pepperidge Farm from a home baking venture into a major commercial bakery brand.
  • C. Patricia Bloomfield
    Patricia Bloomfield is known as the wife of renowned Dutch conductor Bernard Haitink.
  • D. Frances Neagley
    Frances Neagley is a highly skilled, fiercely loyal former U.S. Army MP and close ally of Jack Reacher who frequently assists him in investigations throughout Lee Child’s thriller series.
  • E. Gillian Siddall
    Gillian Siddall is a Canadian academic and university administrator who serves as president of Lakehead University.
  • 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_69d8b9175fec8190af865699b4e64d8c completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e514f594f88190a683e6224e091593 completed April 19, 2026, 5:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03cc266d608190988a7250a2626575 completed May 13, 2026, 12:56 a.m.
NEDg Description generation batch_6a03cd30105c8190925ebd435d7b2925 completed May 13, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_6a03cdac1cc48190a1056371bed04c90 completed May 13, 2026, 1:02 a.m.
Created at: April 10, 2026, 10:37 a.m.