Triple

T19546236
Position Surface form Disambiguated ID Type / Status
Subject James Arness E489057 entity
Predicate notableRole P22 FINISHED
Object Marshal Matt Dillon 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: Marshal Matt Dillon | Statement: [James Arness, notableRole, Marshal Matt Dillon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marshal Matt Dillon
Context triple: [James Arness, notableRole, Marshal Matt Dillon]
  • A. Dean Dillon
    Dean Dillon is an American country music singer-songwriter best known for writing numerous hit songs for George Strait and other major country artists.
  • B. Matt Dillon chosen
    Matt Dillon is the fictional U.S. Marshal who serves as the central lawman and protagonist of the long-running Western series "Gunsmoke."
  • C. Matt Dillon
    Matt Dillon is an American actor known for his versatile performances in films ranging from 1980s teen dramas like "The Outsiders" to acclaimed roles in movies such as "Drugstore Cowboy" and "Crash."
  • D. Sam Ryan
    Sam Ryan is one of the children of Janna Little Ryan and her husband, American politician Paul Ryan.
  • E. Sam Ryan
    Sam Ryan is the central forensic pathologist and early lead character in the British crime drama series "Silent Witness."
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63876bacc8190b17e2087de679785 completed April 20, 2026, 2:30 p.m.
Created at: April 10, 2026, 1:41 p.m.