Triple

T12439455
Position Surface form Disambiguated ID Type / Status
Subject Outfit E297231 entity
Predicate notableBoss P64131 FINISHED
Object Paul Ricca E297232 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: Paul Ricca | Statement: [Outfit, notableBoss, Paul Ricca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Ricca
Context triple: [Outfit, notableBoss, Paul Ricca]
  • A. Paul Ricca chosen
    Paul Ricca was a prominent mid-20th-century American mob boss who helped lead and shape organized crime in Chicago.
  • B. Gabriele Loria
    Gabriele Loria is an Italian mathematician known for his work in geometry and the history of mathematics.
  • C. Robert Pinget
    Robert Pinget was a French avant-garde novelist and playwright associated with the Nouveau Roman movement and often linked to Samuel Beckett.
  • D. Gilbert Durand
    Gilbert Durand was a French philosopher and anthropologist best known for his influential work on the theory of symbols and the anthropology of the imaginary.
  • E. Simon-Joseph Pellegrin
    Simon-Joseph Pellegrin was an 18th-century French abbé, poet, and prolific opera librettist known for providing texts to composers such as Jean-Philippe Rameau.
  • 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_69f63f0911a08190ba84a20950762e68 completed May 2, 2026, 6:14 p.m.
Created at: April 8, 2026, 9:55 p.m.