Triple

T10781880
Position Surface form Disambiguated ID Type / Status
Subject Frances Marion E254336 entity
Predicate spouse P13 FINISHED
Object Fred Thomson
Fred Thomson was a popular American silent film actor and Western star of the 1920s, known for his athleticism and performances alongside his famous horse, Silver King.
 E890802 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: Fred Thomson | Statement: [Frances Marion, spouse, Fred Thomson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fred Thomson
Context triple: [Frances Marion, spouse, Fred Thomson]
  • A. Howard H. Thomson
    Howard H. Thomson was an architect best known for designing Edinburgh’s prominent concert venue, the Usher Hall.
  • B. Edward K. Thompson
    Edward K. Thompson was an influential American magazine editor best known for his leadership at Life magazine during its mid-20th-century heyday.
  • C. Jerry Thompson
    Jerry Thompson is the fictional investigative reporter in Orson Welles's film "Citizen Kane" who seeks to uncover the meaning behind Charles Foster Kane's final word, "Rosebud."
  • D. Paul Thompson
    Paul Thompson is a musician best known as a member of the alternative rock band Concrete Blonde.
  • E. Paul Thompson
    Paul Thompson is a musician known for his work featured on the track "Run for Cover."
  • 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: Fred Thomson
Triple: [Frances Marion, spouse, Fred Thomson]
Generated description
Fred Thomson was a popular American silent film actor and Western star of the 1920s, known for his athleticism and performances alongside his famous horse, Silver King.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fred Thomson
Target entity description: Fred Thomson was a popular American silent film actor and Western star of the 1920s, known for his athleticism and performances alongside his famous horse, Silver King.
  • A. Howard H. Thomson
    Howard H. Thomson was an architect best known for designing Edinburgh’s prominent concert venue, the Usher Hall.
  • B. Edward K. Thompson
    Edward K. Thompson was an influential American magazine editor best known for his leadership at Life magazine during its mid-20th-century heyday.
  • C. Jerry Thompson
    Jerry Thompson is the fictional investigative reporter in Orson Welles's film "Citizen Kane" who seeks to uncover the meaning behind Charles Foster Kane's final word, "Rosebud."
  • D. Paul Thompson
    Paul Thompson is a musician best known as a member of the alternative rock band Concrete Blonde.
  • E. Paul Thompson
    Paul Thompson is a musician known for his work featured on the track "Run for Cover."
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d732c5618081908f72838ed42ed05c completed April 9, 2026, 5:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7b050ec8190b75877d5724c2aec completed April 15, 2026, 8:40 p.m.
NEDg Description generation batch_69e0026e7900819087327db5f625169c completed April 15, 2026, 9:26 p.m.
NED2 Entity disambiguation (via description) batch_69e0057a7704819096becb74dc261883 completed April 15, 2026, 9:39 p.m.
Created at: April 8, 2026, 9:17 p.m.