Triple

T5056698
Position Surface form Disambiguated ID Type / Status
Subject Tommy Dorsey E113919 entity
Predicate spouse P13 FINISHED
Object Patricia Dane
Patricia Dane was an American film actress of the 1940s who appeared in several MGM productions and was briefly married to bandleader Tommy Dorsey.
 E503269 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: Patricia Dane | Statement: [Tommy Dorsey, spouse, Patricia Dane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Patricia Dane
Context triple: [Tommy Dorsey, spouse, Patricia Dane]
  • A. Carol Seaver
    Carol Seaver is the intelligent, ambitious, and sometimes neurotic teenage daughter in the family sitcom "Growing Pains."
  • B. Beverly Gage
    Beverly Gage is an American historian and Yale professor known for her scholarship on 20th-century U.S. political history and her acclaimed biography of FBI director J. Edgar Hoover.
  • C. Patricia P. Frank
    Patricia P. Frank is a screenwriter known for her work on the classic comedy film "The Court Jester."
  • D. Pamela Frank
    Pamela Frank is the second wife of singer and civil rights activist Harry Belafonte, known primarily for her long-term marriage to the entertainer.
  • E. Pamela Frank
    Pamela Frank is an acclaimed American violinist renowned for her expressive performances and influential teaching career.
  • 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: Patricia Dane
Triple: [Tommy Dorsey, spouse, Patricia Dane]
Generated description
Patricia Dane was an American film actress of the 1940s who appeared in several MGM productions and was briefly married to bandleader Tommy Dorsey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Patricia Dane
Target entity description: Patricia Dane was an American film actress of the 1940s who appeared in several MGM productions and was briefly married to bandleader Tommy Dorsey.
  • A. Carol Seaver
    Carol Seaver is the intelligent, ambitious, and sometimes neurotic teenage daughter in the family sitcom "Growing Pains."
  • B. Beverly Gage
    Beverly Gage is an American historian and Yale professor known for her scholarship on 20th-century U.S. political history and her acclaimed biography of FBI director J. Edgar Hoover.
  • C. Patricia P. Frank
    Patricia P. Frank is a screenwriter known for her work on the classic comedy film "The Court Jester."
  • D. Pamela Frank
    Pamela Frank is an acclaimed American violinist renowned for her expressive performances and influential teaching career.
  • E. Pamela Frank
    Pamela Frank is the second wife of singer and civil rights activist Harry Belafonte, known primarily for her long-term marriage to the entertainer.
  • 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_69bd443aa1f88190abb992d138f2cf42 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7450312881908d4e3576ca65f7fb completed March 20, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69beef988a0c8190a6c7898df8e94a6e completed March 21, 2026, 7:20 p.m.
NEDg Description generation batch_69bef20c05c88190ab134bc54f81d790 completed March 21, 2026, 7:31 p.m.
NED2 Entity disambiguation (via description) batch_69bef25db45c819093c7e07eab6b8539 completed March 21, 2026, 7:32 p.m.
Created at: March 20, 2026, 1:38 p.m.