Triple

T8982218
Position Surface form Disambiguated ID Type / Status
Subject John Gavin E214558 entity
Predicate spouse P13 FINISHED
Object Constance Towers
Constance Towers is an American actress and singer known for her work in film, television, and on Broadway, including notable roles in "The Naked Kiss" and the soap opera "General Hospital."
 E769054 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: Constance Towers | Statement: [John Gavin, spouse, Constance Towers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Constance Towers
Context triple: [John Gavin, spouse, Constance Towers]
  • A. Arlene Miles
    Arlene Miles was the first wife of American jazz singer and songwriter Mel Tormé.
  • B. Cathy Crawford
    Cathy Crawford was one of the adopted daughters of legendary Hollywood actress Joan Crawford.
  • C. Sondra Spriggs
    Sondra Spriggs is known as the former spouse of American actor Mykelti Williamson.
  • D. Rachel Marron
    Rachel Marron is a famous pop singer and actress who becomes the client and love interest of a former Secret Service agent in the romantic thriller film "The Bodyguard."
  • E. Marilou York
    Marilou York is an American dental hygienist best known as the longtime wife of actor Mark Hamill.
  • 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: Constance Towers
Triple: [John Gavin, spouse, Constance Towers]
Generated description
Constance Towers is an American actress and singer known for her work in film, television, and on Broadway, including notable roles in "The Naked Kiss" and the soap opera "General Hospital."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Constance Towers
Target entity description: Constance Towers is an American actress and singer known for her work in film, television, and on Broadway, including notable roles in "The Naked Kiss" and the soap opera "General Hospital."
  • A. Arlene Miles
    Arlene Miles was the first wife of American jazz singer and songwriter Mel Tormé.
  • B. Cathy Crawford
    Cathy Crawford was one of the adopted daughters of legendary Hollywood actress Joan Crawford.
  • C. Sondra Spriggs
    Sondra Spriggs is known as the former spouse of American actor Mykelti Williamson.
  • D. Rachel Marron
    Rachel Marron is a famous pop singer and actress who becomes the client and love interest of a former Secret Service agent in the romantic thriller film "The Bodyguard."
  • E. Marilou York
    Marilou York is an American dental hygienist best known as the longtime wife of actor Mark Hamill.
  • 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_69cfc97617908190859d1e27248f43cf completed April 3, 2026, 2:06 p.m.
NEDg Description generation batch_69cfca211ea48190973fcf3c9fe68929 completed April 3, 2026, 2:09 p.m.
NED2 Entity disambiguation (via description) batch_69cfca84937881909707497d733218e5 completed April 3, 2026, 2:11 p.m.
Created at: March 30, 2026, 7:03 p.m.