Triple

T17714000
Position Surface form Disambiguated ID Type / Status
Subject Hank Mitchell E442141 entity
Predicate portrayedBy P1507 FINISHED
Object Brian Kerwin 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: Brian Kerwin | Statement: [Hank Mitchell, portrayedBy, Brian Kerwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Kerwin
Context triple: [Hank Mitchell, portrayedBy, Brian Kerwin]
  • A. Brian Kerwin chosen
    Brian Kerwin is an American actor known for his work in film, television, and theater, including roles in movies like "King Kong Lives" and various popular TV series.
  • B. John Keister
    John Keister is an American comedian and television personality best known as a longtime cast member and host of the Seattle-based sketch comedy show "Almost Live!".
  • C. Brian Warfield
    Brian Warfield is an Irish musician and songwriter best known as a member of the folk band The Wolfe Tones.
  • D. Kirk Stievely
    Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
  • E. Ken Nelson
    Ken Nelson was an influential American record producer best known for his work with country and pop artists at Capitol Records during the mid-20th century.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729cebd08190872be96a26d0f7ce completed April 19, 2026, 6:13 a.m.
Created at: April 10, 2026, 10:06 a.m.