Triple

T5929547
Position Surface form Disambiguated ID Type / Status
Subject Letterkenny E131899 entity
Predicate hasSpinOff P7226 FINISHED
Object Shoresy
Shoresy is a Canadian comedy television series that follows the foul-mouthed, chirp-happy hockey player from Letterkenny as he joins a struggling senior AAA team in Sudbury.
E554993 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: Shoresy | Statement: [Letterkenny, hasSpinOff, Shoresy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shoresy
Context triple: [Letterkenny, hasSpinOff, Shoresy]
  • A. Sandy-boy
    Sandy-boy is a diminutive or affectionate nickname derived from the given name Sandy.
  • B. Willie the Wave
    Willie the Wave is the anthropomorphic wave mascot representing Pepperdine University's athletic teams and school spirit.
  • C. Kenny Sailors
    Kenny Sailors was an American basketball player best known for popularizing the modern jump shot and starring in both college and professional leagues in the 1940s and 1950s.
  • D. Hooperman
    Hooperman is an American television dramedy series from the late 1980s starring John Ritter as a San Francisco police inspector balancing his personal and professional life.
  • E. Cory
    Cory is a masculine given name commonly used in English-speaking countries, often as a short form of names like Corey or Cornelius.
  • 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: Shoresy
Triple: [Letterkenny, hasSpinOff, Shoresy]
Generated description
Shoresy is a Canadian comedy television series that follows the foul-mouthed, chirp-happy hockey player from Letterkenny as he joins a struggling senior AAA team in Sudbury.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shoresy
Target entity description: Shoresy is a Canadian comedy television series that follows the foul-mouthed, chirp-happy hockey player from Letterkenny as he joins a struggling senior AAA team in Sudbury.
  • A. Sandy-boy
    Sandy-boy is a diminutive or affectionate nickname derived from the given name Sandy.
  • B. Willie the Wave
    Willie the Wave is the anthropomorphic wave mascot representing Pepperdine University's athletic teams and school spirit.
  • C. Kenny Sailors
    Kenny Sailors was an American basketball player best known for popularizing the modern jump shot and starring in both college and professional leagues in the 1940s and 1950s.
  • D. Hooperman
    Hooperman is an American television dramedy series from the late 1980s starring John Ritter as a San Francisco police inspector balancing his personal and professional life.
  • E. Cory
    Cory is a masculine given name commonly used in English-speaking countries, often as a short form of names like Corey or Cornelius.
  • 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_69c0085b75e88190a632f9691f9da48b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0389ac4b881908d551e7e29f89888 completed March 22, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0c059b08c8190aec3a8ee0119abed completed March 23, 2026, 4:23 a.m.
NEDg Description generation batch_69c0c11933d081909bb5133ce3bcf7cc completed March 23, 2026, 4:27 a.m.
NED2 Entity disambiguation (via description) batch_69c0c1c31b108190af16c66f6e8a4c25 completed March 23, 2026, 4:29 a.m.
Created at: March 22, 2026, 4 p.m.