Triple

T23140255
Position Surface form Disambiguated ID Type / Status
Subject Beastly E577440 entity
Predicate editedBy P1954 FINISHED
Object Matt Friedman NE NERFINISHED

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: Matt Friedman | Statement: [Beastly, editedBy, Matt Friedman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Friedman
Context triple: [Beastly, editedBy, Matt Friedman]
  • A. Matt Friedman chosen
    Matt Friedman is a film editor best known for his work on major Hollywood comedies and studio features.
  • B. Josh Friedman
    Josh Friedman is an American screenwriter and producer known for his work on films and television series such as "War of the Worlds," "Terminator: The Sarah Connor Chronicles," and contributions to major genre franchises.
  • C. Marc Friedland
    Marc Friedland is an American designer best known for his high-end custom invitations and stationery for Hollywood events and celebrities.
  • D. Brian Fresco
    Brian Fresco is a Chicago-based rapper known as a member of the SaveMoney collective alongside artists like Chance the Rapper and Vic Mensa.
  • E. Patri Friedman
    Patri Friedman is an American libertarian activist and theorist best known for promoting seasteading and innovative approaches to governance and political experimentation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18ec922b481908084eee6a95aef83 completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4 p.m.