Triple

T12542368
Position Surface form Disambiguated ID Type / Status
Subject Almost Live! E299872 entity
Predicate hasCastMember P2308 FINISHED
Object 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!".
E1043157 NE FINISHED

How this triple was built (4 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 Keister | Statement: [Almost Live!, hasCastMember, John Keister]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Keister
Context triple: [Almost Live!, hasCastMember, John Keister]
  • A. Kirk Stievely
    Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
  • B. Joss Christensen
    Joss Christensen is an American freestyle skier best known for winning the inaugural Olympic gold medal in men's slopestyle skiing at the 2014 Winter Olympics in Sochi.
  • C. George Keister
    George Keister was an American architect best known for designing prominent early 20th-century theaters and commercial buildings in New York City.
  • D. Kip Pardue
    Kip Pardue is an American actor and former model best known for his roles in films like "Remember the Titans" and "Driven."
  • E. Brian Kerwin
    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.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: John Keister
Triple: [Almost Live!, hasCastMember, John Keister]
Generated description
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!".
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Keister
Target entity description: 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!".
  • A. Kirk Stievely
    Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
  • B. Joss Christensen
    Joss Christensen is an American freestyle skier best known for winning the inaugural Olympic gold medal in men's slopestyle skiing at the 2014 Winter Olympics in Sochi.
  • C. George Keister
    George Keister was an American architect best known for designing prominent early 20th-century theaters and commercial buildings in New York City.
  • D. Kip Pardue
    Kip Pardue is an American actor and former model best known for his roles in films like "Remember the Titans" and "Driven."
  • E. Brian Kerwin
    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.
  • F. None of above. chosen

Provenance (5 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9547d6df4819080db8415d386ed38 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f746077b288190b8ca7927352a7904 completed May 3, 2026, 12:56 p.m.
NEDg Description generation batch_69f749d6ce888190b4a07462e9b8a40e completed May 3, 2026, 1:12 p.m.
NED2 Entity disambiguation (via description) batch_69f74a2fed2c8190b006575d88c01bdd completed May 3, 2026, 1:14 p.m.
Created at: April 8, 2026, 9:57 p.m.