Triple

T6628314
Position Surface form Disambiguated ID Type / Status
Subject Presumed Innocent E149857 entity
Predicate producer P490 FINISHED
Object Mark Rosenberg E158459 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: Mark Rosenberg | Statement: [Presumed Innocent, producer, Mark Rosenberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Rosenberg
Context triple: [Presumed Innocent, producer, Mark Rosenberg]
  • A. Mark Rosenberg chosen
    Mark Rosenberg was an American film producer known for his work on notable movies of the 1980s and early 1990s.
  • B. Scott Rosenberg
    Scott Rosenberg is an American screenwriter and producer known for writing high-profile films such as "Con Air," "Gone in 60 Seconds," and "High Fidelity."
  • C. Matthew Weisman
    Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
  • D. Scott Rothman
    Scott Rothman is an American screenwriter best known for co-writing the sports drama film "Draft Day."
  • E. Anthony Meyer
    Anthony Meyer is a British politician and former Conservative Member of Parliament best known for mounting a symbolic leadership challenge against Prime Minister Margaret Thatcher in 1989.
  • 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_69c687ee50048190aa151765bef16193 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6afa4a08481908cb5a554f388f32a completed March 27, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70ae8248081909a0f6628583f4626 completed March 27, 2026, 10:55 p.m.
Created at: March 27, 2026, 1:59 p.m.