Triple

T16331352
Position Surface form Disambiguated ID Type / Status
Subject Crashing Towers E396559 entity
Predicate featuresActor P15562 FINISHED
Object Art Dillard
Art Dillard was an American film actor and stuntman known for his work in early Westerns and action serials.
E1211567 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: Art Dillard | Statement: [Crashing Towers, featuresActor, Art Dillard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Art Dillard
Context triple: [Crashing Towers, featuresActor, Art Dillard]
  • A. Art Davie
    Art Davie is an American entrepreneur and combat sports promoter best known as the co-creator and original promoter of the Ultimate Fighting Championship (UFC).
  • B. James Trombly
    James Trombly is an author known for writing Western-themed works centered on cowboy life and culture.
  • C. Doug Dillard
    Doug Dillard was an influential American bluegrass banjo player and musician best known for his work with The Dillards and his role in popularizing bluegrass in the 1960s.
  • D. Artis Gilmore
    Artis Gilmore is a Hall of Fame American basketball center renowned for his dominant shot-blocking, rebounding, and scoring during a stellar career in both the ABA and NBA.
  • E. William Reynolds
    William Reynolds is a film editor best known for his work on the classic crime drama "The Godfather."
  • 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: Art Dillard
Triple: [Crashing Towers, featuresActor, Art Dillard]
Generated description
Art Dillard was an American film actor and stuntman known for his work in early Westerns and action serials.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Art Dillard
Target entity description: Art Dillard was an American film actor and stuntman known for his work in early Westerns and action serials.
  • A. Art Davie
    Art Davie is an American entrepreneur and combat sports promoter best known as the co-creator and original promoter of the Ultimate Fighting Championship (UFC).
  • B. James Trombly
    James Trombly is an author known for writing Western-themed works centered on cowboy life and culture.
  • C. Doug Dillard
    Doug Dillard was an influential American bluegrass banjo player and musician best known for his work with The Dillards and his role in popularizing bluegrass in the 1960s.
  • D. Artis Gilmore
    Artis Gilmore is a Hall of Fame American basketball center renowned for his dominant shot-blocking, rebounding, and scoring during a stellar career in both the ABA and NBA.
  • E. William Reynolds
    William Reynolds is a film editor best known for his work on the classic crime drama "The Godfather."
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2c4dfd9688190a749e48ebc055baf completed April 17, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a003c4ca7ac819098cae8aabfe7e395 completed May 10, 2026, 8:05 a.m.
NEDg Description generation batch_6a003e3b113c819083e1abc512631e2b completed May 10, 2026, 8:13 a.m.
NED2 Entity disambiguation (via description) batch_6a003eb6aa748190b0c8866af405794a completed May 10, 2026, 8:15 a.m.
Created at: April 10, 2026, 5:07 a.m.