Triple

T20448915
Position Surface form Disambiguated ID Type / Status
Subject The Sum of Us E501594 entity
Predicate starring P1507 FINISHED
Object John Polson 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: John Polson | Statement: [The Sum of Us, starring, John Polson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Polson
Context triple: [The Sum of Us, starring, John Polson]
  • A. John Polson chosen
    John Polson is an Australian actor and filmmaker best known internationally for directing thrillers such as "Swimfan" and "Hide and Seek."
  • B. Stephen Rennicks
    Stephen Rennicks is an Irish composer best known for his film scores, particularly his long-standing collaboration with director Lenny Abrahamson.
  • C. Tom Brooke
    Tom Brooke is a British character actor known for his work in film, television, and theatre, including roles in projects like "Preacher," "Game of Thrones," and various acclaimed UK dramas.
  • D. Martin Blunt
    Martin Blunt is an English musician best known as the longtime bassist and founding member of the alternative rock band The Charlatans.
  • E. Graham Baldwin
    Graham Baldwin is a British academic and university leader who serves as the vice-chancellor of the University of Central Lancashire.
  • 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_69e0b4ac0a1c81908845d0f8a56abce8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e68cfffae4819086c727f4143c2737 completed April 20, 2026, 8:30 p.m.
Created at: April 16, 2026, 11:32 a.m.