Triple

T12699838
Position Surface form Disambiguated ID Type / Status
Subject Ellen Morgan E303429 entity
Predicate hasFriend P8712 FINISHED
Object Spence Kovak
Spence Kovak is a supporting character on the 1990s sitcom "Ellen," known as one of Ellen Morgan’s close friends.
E998341 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: Spence Kovak | Statement: [Ellen Morgan, hasFriend, Spence Kovak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spence Kovak
Context triple: [Ellen Morgan, hasFriend, Spence Kovak]
  • A. Dane Krager
    Dane Krager is an American indoor football executive and former player who serves as the general manager of the Frisco Fighters in the Indoor Football League.
  • B. Ryan Johansen
    Ryan Johansen is a Canadian professional ice hockey center who has played in the NHL for teams including the Columbus Blue Jackets and Nashville Predators.
  • C. Jordan Krause
    Jordan Krause is a film producer known for working on the documentary "Love, Antosha," which explores the life and legacy of actor Anton Yelchin.
  • D. Nick Cogley
    Nick Cogley was an early 20th-century American character actor known for his roles in silent films.
  • E. Kyle Davidson
    Kyle Davidson is a Canadian ice hockey executive best known as the general manager responsible for leading the NHL’s Chicago Blackhawks roster rebuild.
  • 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: Spence Kovak
Triple: [Ellen Morgan, hasFriend, Spence Kovak]
Generated description
Spence Kovak is a supporting character on the 1990s sitcom "Ellen," known as one of Ellen Morgan’s close friends.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Spence Kovak
Target entity description: Spence Kovak is a supporting character on the 1990s sitcom "Ellen," known as one of Ellen Morgan’s close friends.
  • A. Dane Krager
    Dane Krager is an American indoor football executive and former player who serves as the general manager of the Frisco Fighters in the Indoor Football League.
  • B. Ryan Johansen
    Ryan Johansen is a Canadian professional ice hockey center who has played in the NHL for teams including the Columbus Blue Jackets and Nashville Predators.
  • C. Jordan Krause
    Jordan Krause is a film producer known for working on the documentary "Love, Antosha," which explores the life and legacy of actor Anton Yelchin.
  • D. Nick Cogley
    Nick Cogley was an early 20th-century American character actor known for his roles in silent films.
  • E. Kyle Davidson
    Kyle Davidson is a Canadian ice hockey executive best known as the general manager responsible for leading the NHL’s Chicago Blackhawks roster rebuild.
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ef65ac8190aedf9ade3a68e24e completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671b27790819085f0f03af33f8f21 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f6740129688190b286ce7acb4848c7 completed May 2, 2026, 10 p.m.
NED2 Entity disambiguation (via description) batch_69f675249d248190933421df49d3a2ab completed May 2, 2026, 10:05 p.m.
Created at: April 9, 2026, 5:22 p.m.