Triple

T7674579
Position Surface form Disambiguated ID Type / Status
Subject Bullseye E173829 entity
Predicate voiceActor P1507 FINISHED
Object Tony Green
Tony Green is a voice actor best known for providing the voice of the Marvel Comics villain Bullseye in animated media.
 E683462 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: Tony Green | Statement: [Bullseye, voiceActor, Tony Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tony Green
Context triple: [Bullseye, voiceActor, Tony Green]
  • A. Scott Green
    Scott Green is a former National Football League official best known for serving as a referee in multiple Super Bowls.
  • B. Scott Green
    Scott Green is an American higher-education administrator and business executive who serves as president of the University of Idaho.
  • C. Ed Green
    Ed Green is a fictional New York City homicide detective on the television series "Law & Order," known for his sharp instincts, moral complexity, and long-running partnership with senior detectives.
  • D. Mark Greene
    Mark Greene is a central fictional emergency physician and one of the original main characters on the television series "ER."
  • E. Dale Hunter
    Dale Hunter is a former Canadian NHL center known for his gritty, physical play and leadership, most notably with the Washington Capitals.
  • 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: Tony Green
Triple: [Bullseye, voiceActor, Tony Green]
Generated description
Tony Green is a voice actor best known for providing the voice of the Marvel Comics villain Bullseye in animated media.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tony Green
Target entity description: Tony Green is a voice actor best known for providing the voice of the Marvel Comics villain Bullseye in animated media.
  • A. Scott Green
    Scott Green is a former National Football League official best known for serving as a referee in multiple Super Bowls.
  • B. Scott Green
    Scott Green is an American higher-education administrator and business executive who serves as president of the University of Idaho.
  • C. Ed Green
    Ed Green is a fictional New York City homicide detective on the television series "Law & Order," known for his sharp instincts, moral complexity, and long-running partnership with senior detectives.
  • D. Mark Greene
    Mark Greene is a central fictional emergency physician and one of the original main characters on the television series "ER."
  • E. Dale Hunter
    Dale Hunter is a former Canadian NHL center known for his gritty, physical play and leadership, most notably with the Washington Capitals.
  • 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_69c6995703e0819081de77361b602e78 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701e1e530819086f49f63ba0b7b42 completed March 27, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8ac9818fc81908d65c03702fc1453 completed March 29, 2026, 4:37 a.m.
NEDg Description generation batch_69c8af2fdd048190ad54dc9a4396d171 completed March 29, 2026, 4:48 a.m.
NED2 Entity disambiguation (via description) batch_69c8afe14810819094a236fb8f96e562 completed March 29, 2026, 4:51 a.m.
Created at: March 27, 2026, 4 p.m.