Triple

T18738119
Position Surface form Disambiguated ID Type / Status
Subject Joshua Malina E458217 entity
Predicate portrayed P1668 FINISHED
Object David Rosen
David Rosen is a principled yet politically embattled U.S. Attorney character on the television drama "Scandal."
E1355579 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: David Rosen | Statement: [Joshua Malina, portrayed, David Rosen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Rosen
Context triple: [Joshua Malina, portrayed, David Rosen]
  • A. Danny Rosenfeld
    Danny Rosenfeld is the son of Irving Rosenfeld, a central con artist character in the film "American Hustle."
  • B. David Saperstein
    David Saperstein is an American author best known for writing the science fiction novel "Cocoon," which was adapted into the popular 1985 film of the same name.
  • C. Michael Nudelman
    Michael Nudelman was an Israeli politician and Knesset member known for representing Russian-speaking immigrants and serving in several immigrant-focused political parties.
  • D. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • E. Michael Rotenberg
    Michael Rotenberg is a television producer and manager best known for his work on popular comedy series including It's Always Sunny in Philadelphia.
  • 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: David Rosen
Triple: [Joshua Malina, portrayed, David Rosen]
Generated description
David Rosen is a principled yet politically embattled U.S. Attorney character on the television drama "Scandal."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Rosen
Target entity description: David Rosen is a principled yet politically embattled U.S. Attorney character on the television drama "Scandal."
  • A. Danny Rosenfeld
    Danny Rosenfeld is the son of Irving Rosenfeld, a central con artist character in the film "American Hustle."
  • B. David Saperstein
    David Saperstein is an American author best known for writing the science fiction novel "Cocoon," which was adapted into the popular 1985 film of the same name.
  • C. Michael Nudelman
    Michael Nudelman was an Israeli politician and Knesset member known for representing Russian-speaking immigrants and serving in several immigrant-focused political parties.
  • D. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • E. Michael Rotenberg
    Michael Rotenberg is a television producer and manager best known for his work on popular comedy series including It's Always Sunny in Philadelphia.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5768b80ac8190bc05628d64f86fc9 completed April 20, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05c535981c8190909d422eda7cb174 completed May 14, 2026, 12:51 p.m.
NEDg Description generation batch_6a05c6de920081909fa458583f487acf completed May 14, 2026, 12:58 p.m.
NED2 Entity disambiguation (via description) batch_6a05c7b75140819085218f4dd5c74a66 completed May 14, 2026, 1:01 p.m.
Created at: April 10, 2026, 11:51 a.m.