Triple

T11407192
Position Surface form Disambiguated ID Type / Status
Subject Rush E270269 entity
Predicate screenwriter P2831 FINISHED
Object Peter Morgan E74595 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: Peter Morgan | Statement: [Rush, screenwriter, Peter Morgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Morgan
Context triple: [Rush, screenwriter, Peter Morgan]
  • A. Peter Morgan chosen
    Peter Morgan is a British screenwriter and playwright best known for his political and historical dramas, including works like The Queen and the series The Crown.
  • B. Mark Lynton
    Mark Lynton was a German-born publishing executive, author, and philanthropist whose legacy in supporting historical scholarship is commemorated by the history prize that bears his name.
  • C. James Graham
    James Graham is the father of American actress Heather Graham.
  • D. James Graham
    James Graham was a 17th-century Scottish nobleman, soldier, and poet best known for leading Royalist forces during the Wars of the Three Kingdoms.
  • E. James Graham
    James Graham is a pseudonym used by British thriller novelist Jack Higgins, famed for his bestselling espionage and war-themed novels.
  • 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_69d6aaddeaa8819088b30ef7b50598c9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8014c820c81908538ba4a08e13230 completed April 9, 2026, 7:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69e58d6eea4c81908319a590d2d9e177 completed April 20, 2026, 2:20 a.m.
Created at: April 8, 2026, 9:34 p.m.