Triple

T15146786
Position Surface form Disambiguated ID Type / Status
Subject Kicking Horse Coffee E361828 entity
Predicate hasProduct P3585 FINISHED
Object Pony Up
Pony Up is a coffee blend produced by the Canadian specialty roaster Kicking Horse Coffee.
 E1140515 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: Pony Up | Statement: [Kicking Horse Coffee, hasProduct, Pony Up]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pony Up
Context triple: [Kicking Horse Coffee, hasProduct, Pony Up]
  • A. Let That Pony Run
    "Let That Pony Run" is a country song recorded by American singer Pam Tillis, known for its storytelling lyrics and success on the country music charts in the early 1990s.
  • B. Tired Pony
    Tired Pony is an indie/alternative supergroup led by Snow Patrol frontman Gary Lightbody, known for its Americana-influenced, folk-rock sound.
  • C. Pony Excess
    Pony Excess is an ESPN 30 for 30 documentary chronicling the rise, scandal, and NCAA "death penalty" of Southern Methodist University’s football program in the 1980s.
  • D. Trick Pony
    Trick Pony is an American country music group known for its energetic honky-tonk style and early-2000s chart hits.
  • E. I Have a Pony
    I Have a Pony is a stand-up comedy album by deadpan comedian Steven Wright, showcasing his signature surreal one-liners and absurd observational humor.
  • 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: Pony Up
Triple: [Kicking Horse Coffee, hasProduct, Pony Up]
Generated description
Pony Up is a coffee blend produced by the Canadian specialty roaster Kicking Horse Coffee.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pony Up
Target entity description: Pony Up is a coffee blend produced by the Canadian specialty roaster Kicking Horse Coffee.
  • A. Let That Pony Run
    "Let That Pony Run" is a country song recorded by American singer Pam Tillis, known for its storytelling lyrics and success on the country music charts in the early 1990s.
  • B. Tired Pony
    Tired Pony is an indie/alternative supergroup led by Snow Patrol frontman Gary Lightbody, known for its Americana-influenced, folk-rock sound.
  • C. Pony Excess
    Pony Excess is an ESPN 30 for 30 documentary chronicling the rise, scandal, and NCAA "death penalty" of Southern Methodist University’s football program in the 1980s.
  • D. Trick Pony
    Trick Pony is an American country music group known for its energetic honky-tonk style and early-2000s chart hits.
  • E. I Have a Pony
    I Have a Pony is a stand-up comedy album by deadpan comedian Steven Wright, showcasing his signature surreal one-liners and absurd observational humor.
  • 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_69d85a0759908190b8a051d2e2a1cbe6 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005c825a481909d00098b0e743365 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69febff02e648190bd10f04a374da227 completed May 9, 2026, 5:02 a.m.
NEDg Description generation batch_69fec08c37dc8190a59289e4ee76beab completed May 9, 2026, 5:05 a.m.
NED2 Entity disambiguation (via description) batch_69fec10cd2d48190ba96885ca604a853 completed May 9, 2026, 5:07 a.m.
Created at: April 10, 2026, 3:07 a.m.