Triple

T1572091
Position Surface form Disambiguated ID Type / Status
Subject John Houseman E33561 entity
Predicate spouse P13 FINISHED
Object Joan Houseman
Joan Houseman was the wife of Romanian-born American actor and producer John Houseman.
 E179491 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: Joan Houseman | Statement: [John Houseman, spouse, Joan Houseman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Joan Houseman
Context triple: [John Houseman, spouse, Joan Houseman]
  • A. Sally Kornbluth
    Sally Kornbluth is an American cell biologist and academic leader who became the 18th president of the Massachusetts Institute of Technology.
  • B. Frances Loeb
    Frances Loeb was an American magazine publisher and philanthropist best known as the former wife of television producer Norman Lear and as the founder of the feminist magazine Ms. Magazine.
  • C. Blanche Knopf
    Blanche Knopf was an influential American publisher and co-founder of the Alfred A. Knopf publishing house, known for championing modernist and international literature.
  • D. Barbara Robbins
    Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
  • E. Jane Belson
    Jane Belson was a British barrister best known as the wife of author Douglas Adams.
  • 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: Joan Houseman
Triple: [John Houseman, spouse, Joan Houseman]
Generated description
Joan Houseman was the wife of Romanian-born American actor and producer John Houseman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Joan Houseman
Target entity description: Joan Houseman was the wife of Romanian-born American actor and producer John Houseman.
  • A. Sally Kornbluth
    Sally Kornbluth is an American cell biologist and academic leader who became the 18th president of the Massachusetts Institute of Technology.
  • B. Frances Loeb
    Frances Loeb was an American magazine publisher and philanthropist best known as the former wife of television producer Norman Lear and as the founder of the feminist magazine Ms. Magazine.
  • C. Blanche Knopf
    Blanche Knopf was an influential American publisher and co-founder of the Alfred A. Knopf publishing house, known for championing modernist and international literature.
  • D. Barbara Robbins
    Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
  • E. Jane Belson
    Jane Belson was a British barrister best known as the wife of author Douglas Adams.
  • 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_69a885f11b048190935025a035302715 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908ba6a4081909f75faf470c53d86 completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4028bc5881909dbe847229dd63bb completed March 8, 2026, 9:23 a.m.
NEDg Description generation batch_69ad41930d208190b34531e3f35fa58b completed March 8, 2026, 9:29 a.m.
NED2 Entity disambiguation (via description) batch_69ad422752348190b42ebc3781a6e8a5 completed March 8, 2026, 9:32 a.m.
Created at: March 4, 2026, 7:27 p.m.