Triple

T20592290
Position Surface form Disambiguated ID Type / Status
Subject Karen Grassle E505959 entity
Predicate spouse P13 FINISHED
Object Leon Russom
Leon Russom is an American character actor known for his work in film and television, including roles in "The Big Lebowski" and various soap operas.
 E1440207 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: Leon Russom | Statement: [Karen Grassle, spouse, Leon Russom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Leon Russom
Context triple: [Karen Grassle, spouse, Leon Russom]
  • A. Billy Russo
    Billy Russo is a Marvel Comics character best known as the disfigured mob hitman-turned-villain Jigsaw, a primary antagonist of the Punisher.
  • B. Jerry Riddle
    Jerry Riddle is a musician best known as a member of the 1960s American rock band The Music Machine.
  • C. Don Stevens
    Don Stevens is a notable individual recognized for achievements significant enough to be distinguished from others sharing the surname Stevens.
  • D. Dan Rydell
    Dan Rydell is a charismatic, quick-witted sports anchor and one of the central protagonists on the television series "Sports Night."
  • E. Martin Ryerson
    Martin Ryerson was an American lawyer, businessman, and philanthropist known for his influential role in education and cultural institutions in the late 19th and early 20th centuries.
  • 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: Leon Russom
Triple: [Karen Grassle, spouse, Leon Russom]
Generated description
Leon Russom is an American character actor known for his work in film and television, including roles in "The Big Lebowski" and various soap operas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Leon Russom
Target entity description: Leon Russom is an American character actor known for his work in film and television, including roles in "The Big Lebowski" and various soap operas.
  • A. Billy Russo
    Billy Russo is a Marvel Comics character best known as the disfigured mob hitman-turned-villain Jigsaw, a primary antagonist of the Punisher.
  • B. Jerry Riddle
    Jerry Riddle is a musician best known as a member of the 1960s American rock band The Music Machine.
  • C. Don Stevens
    Don Stevens is a notable individual recognized for achievements significant enough to be distinguished from others sharing the surname Stevens.
  • D. Dan Rydell
    Dan Rydell is a charismatic, quick-witted sports anchor and one of the central protagonists on the television series "Sports Night."
  • E. Martin Ryerson
    Martin Ryerson was an American lawyer, businessman, and philanthropist known for his influential role in education and cultural institutions in the late 19th and early 20th centuries.
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a97c10f081909daf635e9be0dd22 completed April 20, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08b3e879788190bc3b66d809c4b59b completed May 16, 2026, 6:14 p.m.
NEDg Description generation batch_6a08b485c1548190b800fb3e0fe1b138 completed May 16, 2026, 6:16 p.m.
NED2 Entity disambiguation (via description) batch_6a08b56d00808190b382041bf0cd0173 completed May 16, 2026, 6:20 p.m.
Created at: April 16, 2026, 11:40 a.m.