Triple

T4977759
Position Surface form Disambiguated ID Type / Status
Subject Frank Sheeran E111809 entity
Predicate allegedAssociationWith P2830 FINISHED
Object Bufalino crime family
The Bufalino crime family was a Pennsylvania-based Italian-American Mafia organization known for its influence over labor unions, trucking, and organized crime activities in the mid-20th century United States.
E485612 NE FINISHED

How this triple was built (5 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: Bufalino crime family | Statement: [Frank Sheeran, allegedAssociationWith, Bufalino crime family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bufalino crime family
Context triple: [Frank Sheeran, allegedAssociationWith, Bufalino crime family]
  • A. Luciano crime family
    The Luciano crime family, later known as the Genovese crime family, is one of New York City's most powerful and historically influential Italian-American Mafia organizations.
  • B. Pettingill crime family
    The Pettingill crime family is a notorious Australian criminal clan from Melbourne known for its involvement in drug trafficking, violence, and high-profile confrontations with law enforcement.
  • C. Shelby crime family
    The Shelby crime family is a fictional Birmingham-based gangster clan at the center of the British television series "Peaky Blinders," led by the ambitious and ruthless Thomas Shelby.
  • D. Capone family
    The Capone family is the notorious American crime family best known for producing infamous Chicago mob boss Al Capone and his relatives involved in organized crime during the Prohibition era.
  • E. Italian-American Mafia
    The Italian-American Mafia is a network of organized crime groups in the United States with roots in Sicilian traditions, known for activities such as racketeering, extortion, and illicit gambling, and for its hierarchical, family-based structure.
  • 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: Bufalino crime family
Triple: [Frank Sheeran, allegedAssociationWith, Bufalino crime family]
Generated description
The Bufalino crime family was a Pennsylvania-based Italian-American Mafia organization known for its influence over labor unions, trucking, and organized crime activities in the mid-20th century United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bufalino crime family
Target entity description: The Bufalino crime family was a Pennsylvania-based Italian-American Mafia organization known for its influence over labor unions, trucking, and organized crime activities in the mid-20th century United States.
  • A. Luciano crime family
    The Luciano crime family, later known as the Genovese crime family, is one of New York City's most powerful and historically influential Italian-American Mafia organizations.
  • B. Pettingill crime family
    The Pettingill crime family is a notorious Australian criminal clan from Melbourne known for its involvement in drug trafficking, violence, and high-profile confrontations with law enforcement.
  • C. Shelby crime family
    The Shelby crime family is a fictional Birmingham-based gangster clan at the center of the British television series "Peaky Blinders," led by the ambitious and ruthless Thomas Shelby.
  • D. Capone family
    The Capone family is the notorious American crime family best known for producing infamous Chicago mob boss Al Capone and his relatives involved in organized crime during the Prohibition era.
  • E. Italian-American Mafia
    The Italian-American Mafia is a network of organized crime groups in the United States with roots in Sicilian traditions, known for activities such as racketeering, extortion, and illicit gambling, and for its hierarchical, family-based structure.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: allegedAssociationWith
Context triple: [Frank Sheeran, allegedAssociationWith, Bufalino crime family]
  • A. allegesCollaborationWith
    Indicates that one party claims or asserts that another party has worked together or cooperated with a specified entity.
  • B. allegedAgentOf
    Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
  • C. allegedOrganization
    Indicates that an entity is claimed or suspected to be an organization, without confirming that the claim is true.
  • D. isAssociatedWith chosen
    Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
  • E. leaderAssociatedWith
    Indicates a relationship where a leader is connected or affiliated with a particular entity, such as an organization, group, or cause.
  • F. None of above.

Provenance (6 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_69bd441adc208190b70a033a0741d01e completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd730a7590819088ab8d49c5c88c2f completed March 20, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a0634b48190acb4a1834f5647cf completed March 21, 2026, 12:07 p.m.
NEDg Description generation batch_69be8a9c72848190978797a33d0d83c8 completed March 21, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69be8b3718288190b2fc319fdad0a7c0 completed March 21, 2026, 12:12 p.m.
PD Predicate disambiguation batch_69bd7146e6e881908a55ab2756b631f6 completed March 20, 2026, 4:09 p.m.
Created at: March 20, 2026, 1:33 p.m.