Triple

T8982437
Position Surface form Disambiguated ID Type / Status
Subject Howard Green E214563 entity
Predicate spouse P13 FINISHED
Object Marion M. Green
Marion M. Green is known primarily as the spouse of Howard Green, a Canadian politician who served as a long-time Member of Parliament and cabinet minister.
 E777016 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: Marion M. Green | Statement: [Howard Green, spouse, Marion M. Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marion M. Green
Context triple: [Howard Green, spouse, Marion M. Green]
  • A. Marion E. Bannister
    Marion E. Bannister was the wife of Homer Stillé Cummings, who served as U.S. Attorney General under President Franklin D. Roosevelt.
  • B. Lucile E. Greene
    Lucile E. Greene was an American writer and activist known for her work in civil rights and social justice.
  • C. Marjorie Marshall
    Marjorie Marshall was an American tap dance teacher and the mother of filmmaker and actress Penny Marshall.
  • D. Margaret A. Merritt
    Margaret A. Merritt was an American woman best known as the mother of Janet Lee Bouvier, making her the maternal grandmother of Jacqueline Kennedy Onassis.
  • E. Olive E. Kenny
    Olive E. Kenny was a translator known for rendering works such as Naguib Mahfouz’s novel "Sugar Street" into English.
  • 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: Marion M. Green
Triple: [Howard Green, spouse, Marion M. Green]
Generated description
Marion M. Green is known primarily as the spouse of Howard Green, a Canadian politician who served as a long-time Member of Parliament and cabinet minister.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marion M. Green
Target entity description: Marion M. Green is known primarily as the spouse of Howard Green, a Canadian politician who served as a long-time Member of Parliament and cabinet minister.
  • A. Marion E. Bannister
    Marion E. Bannister was the wife of Homer Stillé Cummings, who served as U.S. Attorney General under President Franklin D. Roosevelt.
  • B. Lucile E. Greene
    Lucile E. Greene was an American writer and activist known for her work in civil rights and social justice.
  • C. Marjorie Marshall
    Marjorie Marshall was an American tap dance teacher and the mother of filmmaker and actress Penny Marshall.
  • D. Margaret A. Merritt
    Margaret A. Merritt was an American woman best known as the mother of Janet Lee Bouvier, making her the maternal grandmother of Jacqueline Kennedy Onassis.
  • E. Olive E. Kenny
    Olive E. Kenny was a translator known for rendering works such as Naguib Mahfouz’s novel "Sugar Street" into English.
  • 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_69ca839ea8b88190922c6a326ffcc0d3 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc67a891e881909e4b84ed82491651 completed April 1, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69d01755d26c819084c6b4967550842e completed April 3, 2026, 7:39 p.m.
NEDg Description generation batch_69d019059e8481909a696575366aa0b6 completed April 3, 2026, 7:46 p.m.
NED2 Entity disambiguation (via description) batch_69d019a2736c8190880c8f3786cf353b completed April 3, 2026, 7:48 p.m.
Created at: March 30, 2026, 7:03 p.m.