Triple

T19397679
Position Surface form Disambiguated ID Type / Status
Subject The Comedian E485235 entity
Predicate screenwriter P2831 FINISHED
Object Lewis Friedman
Lewis Friedman is an American screenwriter known for his work on comedy films and television projects.
E1423364 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: Lewis Friedman | Statement: [The Comedian, screenwriter, Lewis Friedman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lewis Friedman
Context triple: [The Comedian, screenwriter, Lewis Friedman]
  • A. Matthew Friedman
    Matthew Friedman is a film editor best known for his work on the acclaimed 2019 drama "The Farewell."
  • B. Stephen J. Friedman
    Stephen J. Friedman was an American film producer and studio executive known for producing notable Hollywood films from the 1970s through the 1990s.
  • C. Jud Friedman
    Jud Friedman is an American songwriter and producer best known for co-writing major pop and R&B ballads, including hits for artists like Whitney Houston.
  • D. Jan Friedman
    Jan Friedman is a member of the Friedman family, known primarily as the child of economist Rose Friedman and thus part of a prominent lineage in economic thought.
  • E. Jonathan Friedman
    Jonathan Friedman is a relatively common personal name shared by multiple individuals across various professional fields, including academia, law, and the arts.
  • 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: Lewis Friedman
Triple: [The Comedian, screenwriter, Lewis Friedman]
Generated description
Lewis Friedman is an American screenwriter known for his work on comedy films and television projects.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lewis Friedman
Target entity description: Lewis Friedman is an American screenwriter known for his work on comedy films and television projects.
  • A. Matthew Friedman
    Matthew Friedman is a film editor best known for his work on the acclaimed 2019 drama "The Farewell."
  • B. Stephen J. Friedman
    Stephen J. Friedman was an American film producer and studio executive known for producing notable Hollywood films from the 1970s through the 1990s.
  • C. Jud Friedman
    Jud Friedman is an American songwriter and producer best known for co-writing major pop and R&B ballads, including hits for artists like Whitney Houston.
  • D. Jan Friedman
    Jan Friedman is a member of the Friedman family, known primarily as the child of economist Rose Friedman and thus part of a prominent lineage in economic thought.
  • E. Jonathan Friedman
    Jonathan Friedman is a relatively common personal name shared by multiple individuals across various professional fields, including academia, law, and the arts.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62574edd08190b5456108d5e3907e completed April 20, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0861013a1081909a47782a9a1ac1d0 completed May 16, 2026, 12:20 p.m.
NEDg Description generation batch_6a086264e3408190847a995f3538c70b completed May 16, 2026, 12:26 p.m.
NED2 Entity disambiguation (via description) batch_6a0863b6dd84819089344a5ff28bf0cf completed May 16, 2026, 12:31 p.m.
Created at: April 10, 2026, 1:36 p.m.