Triple

T18190299
Position Surface form Disambiguated ID Type / Status
Subject Erskine Caldwell E435514 entity
Predicate spouse P13 FINISHED
Object Virginia Moffett
Virginia Moffett was the wife of American novelist Erskine Caldwell, known for her connection to the author of "Tobacco Road" and "God's Little Acre."
E1500602 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: Virginia Moffett | Statement: [Erskine Caldwell, spouse, Virginia Moffett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Virginia Moffett
Context triple: [Erskine Caldwell, spouse, Virginia Moffett]
  • A. Mary Hoyt
    Mary Hoyt was the birth name of Mary Hoyt Sherman, an American woman known primarily in historical records through her married identity.
  • B. Nancy Moffette Lea
    Nancy Moffette Lea was a 19th-century American woman best known as the mother of Margaret Moffette Lea, who became the wife of Texas president and governor Sam Houston.
  • C. Virginia Herrick
    Virginia Herrick was an American actress and singer active in mid-20th-century film and television.
  • D. Helen Morgendorffer
    Helen Morgendorffer is the career-driven, sharp-tongued mother of Daria Morgendorffer in the animated TV series "Daria."
  • E. Helen Luella Koford
    Helen Luella Koford is the birth name of American actress Terry Moore, known for her work in mid-20th-century Hollywood films.
  • 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: Virginia Moffett
Triple: [Erskine Caldwell, spouse, Virginia Moffett]
Generated description
Virginia Moffett was the wife of American novelist Erskine Caldwell, known for her connection to the author of "Tobacco Road" and "God's Little Acre."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Virginia Moffett
Target entity description: Virginia Moffett was the wife of American novelist Erskine Caldwell, known for her connection to the author of "Tobacco Road" and "God's Little Acre."
  • A. Mary Hoyt
    Mary Hoyt was the birth name of Mary Hoyt Sherman, an American woman known primarily in historical records through her married identity.
  • B. Nancy Moffette Lea
    Nancy Moffette Lea was a 19th-century American woman best known as the mother of Margaret Moffette Lea, who became the wife of Texas president and governor Sam Houston.
  • C. Virginia Herrick
    Virginia Herrick was an American actress and singer active in mid-20th-century film and television.
  • D. Helen Morgendorffer
    Helen Morgendorffer is the career-driven, sharp-tongued mother of Daria Morgendorffer in the animated TV series "Daria."
  • E. Helen Luella Koford
    Helen Luella Koford is the birth name of American actress Terry Moore, known for her work in mid-20th-century Hollywood films.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0016ec08190ae853dbc89865a41 completed April 19, 2026, 2 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a36590b5481909f9b278b8986f9ff completed May 17, 2026, 9:42 p.m.
NEDg Description generation batch_6a0a37879a408190b516ec16a2b23195 completed May 17, 2026, 9:47 p.m.
NED2 Entity disambiguation (via description) batch_6a0a37f8c09c8190a92f78909cfbc6e7 completed May 17, 2026, 9:49 p.m.
Created at: April 10, 2026, 10:31 a.m.