Triple

T20761132
Position Surface form Disambiguated ID Type / Status
Subject Peter Cullen E510978 entity
Predicate voiceRole P12691 FINISHED
Object KARR
KARR is a villainous, self-preservation–obsessed prototype AI car from the 1980s television series "Knight Rider."
 E1449743 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: KARR | Statement: [Peter Cullen, voiceRole, KARR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KARR
Context triple: [Peter Cullen, voiceRole, KARR]
  • A. KAR
    KAR is the ICAO airline designator assigned to the Russian regional carrier Pegas Fly.
  • B. KAR
    KAR is the commonly used abbreviation for the King's African Rifles, a former multi-battalion British colonial regiment recruited from East Africa.
  • C. KÄR
    KÄR is the common abbreviation for Oulun Kärpät, a prominent professional ice hockey club based in Oulu, Finland.
  • D. KARI
    KARI is South Korea's national aerospace research organization responsible for developing space and aeronautical technologies, including satellites and launch vehicles.
  • E. Karry
    Karry is a Chinese automotive brand owned by Chery Automobile that focuses on producing commercial vehicles such as vans and light trucks.
  • 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: KARR
Triple: [Peter Cullen, voiceRole, KARR]
Generated description
KARR is a villainous, self-preservation–obsessed prototype AI car from the 1980s television series "Knight Rider."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KARR
Target entity description: KARR is a villainous, self-preservation–obsessed prototype AI car from the 1980s television series "Knight Rider."
  • A. KAR
    KAR is the ICAO airline designator assigned to the Russian regional carrier Pegas Fly.
  • B. KAR
    KAR is the commonly used abbreviation for the King's African Rifles, a former multi-battalion British colonial regiment recruited from East Africa.
  • C. KÄR
    KÄR is the common abbreviation for Oulun Kärpät, a prominent professional ice hockey club based in Oulu, Finland.
  • D. KARI
    KARI is South Korea's national aerospace research organization responsible for developing space and aeronautical technologies, including satellites and launch vehicles.
  • E. Karry
    Karry is a Chinese automotive brand owned by Chery Automobile that focuses on producing commercial vehicles such as vans and light trucks.
  • 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_69e0b4c909ec8190b05987f1639513f6 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c248701081908ae49fca933e05f6 completed April 21, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08ef84885c8190957b6fd0bf2ef319 completed May 16, 2026, 10:28 p.m.
NEDg Description generation batch_6a08effa455c81908bd6213bed3bdba1 completed May 16, 2026, 10:30 p.m.
NED2 Entity disambiguation (via description) batch_6a08f09a2b688190bf7b026fc4b9977e completed May 16, 2026, 10:32 p.m.
Created at: April 16, 2026, 12:35 p.m.