Triple

T12439717
Position Surface form Disambiguated ID Type / Status
Subject Bugs Moran E297236 entity
Predicate influencedBy P9 FINISHED
Object Dean O’Banion E297237 NE FINISHED

How this triple was built (2 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: Dean O’Banion | Statement: [Bugs Moran, influencedBy, Dean O’Banion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dean O’Banion
Context triple: [Bugs Moran, influencedBy, Dean O’Banion]
  • A. Dean O’Banion chosen
    Dean O’Banion was a prominent Irish-American mobster and leader of Chicago’s North Side Gang during the Prohibition era.
  • B. Louis Capone
    Louis Capone was an American mobster and hitman associated with the New York City underworld, particularly the Murder, Inc. enforcement arm of the Mafia.
  • C. Bugsy Calhoune
    Bugsy Calhoune is a hip-hop artist known for his collaborations with the rapper and producer Quick.
  • D. Billy L. Sullivan
    Billy L. Sullivan is an American actor best known for his role on the sitcom "The Golden Palace."
  • E. Big Jim Colosimo
    Big Jim Colosimo was an early 20th-century Chicago crime boss who built a powerful vice empire and helped lay the groundwork for the city’s later organized crime syndicates.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ada166c48190b902972cd2408fa3 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d8dc0f881908a3da736d8947ce1 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64b9d34848190b02311ada2572440 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:55 p.m.