Triple

T11121336
Position Surface form Disambiguated ID Type / Status
Subject Aaron Spelling E263022 entity
Predicate spouse P13 FINISHED
Object Carol Jean Wagner
Carol Jean Wagner is known as the first wife of prolific American television producer Aaron Spelling.
E906423 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: Carol Jean Wagner | Statement: [Aaron Spelling, spouse, Carol Jean Wagner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Jean Wagner
Context triple: [Aaron Spelling, spouse, Carol Jean Wagner]
  • A. Betsy Rue
    Betsy Rue is an American actress best known for her roles in horror and thriller films, including her appearance in the slasher movie "My Bloody Valentine 3D."
  • B. Mary Brodbar
    Mary Brodbar was the second wife of architect William Wesley Peters, a close associate and son-in-law of Frank Lloyd Wright.
  • C. Ann Wagner
    Ann Wagner is the mother of American actress and businesswoman Priscilla Presley.
  • D. Jeanne Weaver
    Jeanne Weaver is a member of the 2nd Massachusetts Militia Regiment, a state military unit associated with Massachusetts.
  • E. Diandra Luker
    Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
  • 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: Carol Jean Wagner
Triple: [Aaron Spelling, spouse, Carol Jean Wagner]
Generated description
Carol Jean Wagner is known as the first wife of prolific American television producer Aaron Spelling.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carol Jean Wagner
Target entity description: Carol Jean Wagner is known as the first wife of prolific American television producer Aaron Spelling.
  • A. Betsy Rue
    Betsy Rue is an American actress best known for her roles in horror and thriller films, including her appearance in the slasher movie "My Bloody Valentine 3D."
  • B. Mary Brodbar
    Mary Brodbar was the second wife of architect William Wesley Peters, a close associate and son-in-law of Frank Lloyd Wright.
  • C. Ann Wagner
    Ann Wagner is the mother of American actress and businesswoman Priscilla Presley.
  • D. Jeanne Weaver
    Jeanne Weaver is a member of the 2nd Massachusetts Militia Regiment, a state military unit associated with Massachusetts.
  • E. Diandra Luker
    Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
  • 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79af911b881908168f23a4918231c completed April 9, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d8406988190837a16d7ad8048d1 completed April 19, 2026, 1:19 a.m.
NEDg Description generation batch_69e4374700b881908ebb185ae020487b completed April 19, 2026, 2 a.m.
NED2 Entity disambiguation (via description) batch_69e4399385c08190852c3cbd730a1f11 completed April 19, 2026, 2:10 a.m.
Created at: April 8, 2026, 9:28 p.m.