Triple

T16573886
Position Surface form Disambiguated ID Type / Status
Subject American Buffalo E402659 entity
Predicate hasCharacter P2308 FINISHED
Object Bobby
Bobby is a character in David Mamet’s play "American Buffalo," typically portrayed as a young, somewhat naive accomplice drawn into a small-time robbery scheme.
 E1221131 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: Bobby | Statement: [American Buffalo, hasCharacter, Bobby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bobby
Context triple: [American Buffalo, hasCharacter, Bobby]
  • A. Bobby
    "Bobby" is a film directed by Michael Barrett, best known for its portrayal of the events surrounding the assassination of U.S. Senator Robert F. Kennedy.
  • B. Bobby
    "Bobby" is a landmark 1973 Hindi romantic film directed by Raj Kapoor, celebrated for launching Dimple Kapadia to stardom and popularizing youthful love stories in Indian cinema.
  • C. Bobby
    Bobby is a fictional character known for performing the song "Being Alive."
  • D. Bobby
    Bobby is a Texas Ranger character known for his role in law enforcement within the state of Texas.
  • E. Bobby
    Bobby is a family name that can function as a surname in English-speaking contexts.
  • 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: Bobby
Triple: [American Buffalo, hasCharacter, Bobby]
Generated description
Bobby is a character in David Mamet’s play "American Buffalo," typically portrayed as a young, somewhat naive accomplice drawn into a small-time robbery scheme.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bobby
Target entity description: Bobby is a character in David Mamet’s play "American Buffalo," typically portrayed as a young, somewhat naive accomplice drawn into a small-time robbery scheme.
  • A. Bobby
    Bobby is a fictional character from the film "Loosies," a romantic comedy-drama about a New York City pickpocket whose life changes when confronted with unexpected responsibility.
  • B. Bobby
    Bobby is a Texas Ranger character known for his role in law enforcement within the state of Texas.
  • C. Bobby
    Bobby is the nickname of Bobby Elvis, a fictional character from the television series "Sons of Anarchy."
  • D. Bobby
    Bobby is a fictional character known for performing the song "Being Alive."
  • E. Bobby
    "Bobby" is a film directed by Michael Barrett, best known for its portrayal of the events surrounding the assassination of U.S. Senator Robert F. Kennedy.
  • 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3595ab9dc81909b774f6d9c17d6dd completed April 18, 2026, 10:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006eea409c8190808170a0b3f4bd17 completed May 10, 2026, 11:41 a.m.
NEDg Description generation batch_6a006f7ca0dc8190a75d84d9ffbf83e0 completed May 10, 2026, 11:43 a.m.
NED2 Entity disambiguation (via description) batch_6a00705453c081909e8401024e92b5aa completed May 10, 2026, 11:47 a.m.
Created at: April 10, 2026, 5:16 a.m.