Triple

T17739839
Position Surface form Disambiguated ID Type / Status
Subject John Agar E442822 entity
Predicate spouse P13 FINISHED
Object Loretta Combs
Loretta Combs was the first wife of American actor John Agar, known primarily for her marriage to him before his later, higher-profile unions.
 E1294550 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: Loretta Combs | Statement: [John Agar, spouse, Loretta Combs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Loretta Combs
Context triple: [John Agar, spouse, Loretta Combs]
  • A. Lee Ann Womack
    Lee Ann Womack is an American country music singer best known for her hit song "I Hope You Dance" and her traditional country vocal style.
  • B. Lili-Rose Womack
    Lili-Rose Womack is the daughter of English actress and singer Samantha Womack.
  • C. Kimberly Williams-Paisley
    Kimberly Williams-Paisley is an American actress best known for her role in the "Father of the Bride" films and for her work in television series such as "According to Jim."
  • D. Reba McEntire
    Reba McEntire is an American country music singer, songwriter, and actress often called the "Queen of Country" for her decades-long influence and success in the genre.
  • E. Lorrie Morgan
    Lorrie Morgan is an American country music singer known for her emotive vocal style and a string of hits since the late 1980s.
  • 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: Loretta Combs
Triple: [John Agar, spouse, Loretta Combs]
Generated description
Loretta Combs was the first wife of American actor John Agar, known primarily for her marriage to him before his later, higher-profile unions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Loretta Combs
Target entity description: Loretta Combs was the first wife of American actor John Agar, known primarily for her marriage to him before his later, higher-profile unions.
  • A. Lee Ann Womack
    Lee Ann Womack is an American country music singer best known for her hit song "I Hope You Dance" and her traditional country vocal style.
  • B. Lili-Rose Womack
    Lili-Rose Womack is the daughter of English actress and singer Samantha Womack.
  • C. Kimberly Williams-Paisley
    Kimberly Williams-Paisley is an American actress best known for her role in the "Father of the Bride" films and for her work in television series such as "According to Jim."
  • D. Reba McEntire
    Reba McEntire is an American country music singer, songwriter, and actress often called the "Queen of Country" for her decades-long influence and success in the genre.
  • E. Lorrie Morgan
    Lorrie Morgan is an American country music singer known for her emotive vocal style and a string of hits since the late 1980s.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47acc2610819099451b02bb51891f completed April 19, 2026, 6:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a031b149edc81909cb2a14a54c11d02 completed May 12, 2026, 12:20 p.m.
NEDg Description generation batch_6a031b90f94881908655f8bea05ecf0a completed May 12, 2026, 12:22 p.m.
NED2 Entity disambiguation (via description) batch_6a031be43c8c8190bcd67b9b6a2bce9e completed May 12, 2026, 12:24 p.m.
Created at: April 10, 2026, 10:09 a.m.