Triple

T16457588
Position Surface form Disambiguated ID Type / Status
Subject 50/50 E399720 entity
Predicate character P662 FINISHED
Object Kyle Hirons
Kyle Hirons is a character from the 2011 comedy film "50/50," which follows a young man's struggle with a cancer diagnosis.
 E1214695 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: Kyle Hirons | Statement: [50/50, character, Kyle Hirons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kyle Hirons
Context triple: [50/50, character, Kyle Hirons]
  • A. Alex Heffes
    Alex Heffes is a British film composer known for his scores to major feature films and documentaries, including the biographical drama "Mandela: Long Walk to Freedom."
  • B. Jonny Harris
    Jonny Harris is a Canadian actor and comedian best known for his role as Constable George Crabtree on the television series "Murdoch Mysteries."
  • C. Kevin Healey
    Kevin Healey is a British autism campaigner and activist known for his work raising awareness of autism and combating online bullying and discrimination.
  • D. Mike Eley
    Mike Eley is a British cinematographer known for his work on acclaimed films and television dramas.
  • E. Jeremy Hutchinson
    Jeremy Hutchinson is an American attorney and former Arkansas state legislator who gained prominence both for his political career and subsequent legal troubles involving federal corruption charges.
  • 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: Kyle Hirons
Triple: [50/50, character, Kyle Hirons]
Generated description
Kyle Hirons is a character from the 2011 comedy film "50/50," which follows a young man's struggle with a cancer diagnosis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kyle Hirons
Target entity description: Kyle Hirons is a character from the 2011 comedy film "50/50," which follows a young man's struggle with a cancer diagnosis.
  • A. Alex Heffes
    Alex Heffes is a British film composer known for his scores to major feature films and documentaries, including the biographical drama "Mandela: Long Walk to Freedom."
  • B. Jonny Harris
    Jonny Harris is a Canadian actor and comedian best known for his role as Constable George Crabtree on the television series "Murdoch Mysteries."
  • C. Kevin Healey
    Kevin Healey is a British autism campaigner and activist known for his work raising awareness of autism and combating online bullying and discrimination.
  • D. Mike Eley
    Mike Eley is a British cinematographer known for his work on acclaimed films and television dramas.
  • E. Jeremy Hutchinson
    Jeremy Hutchinson is an American attorney and former Arkansas state legislator who gained prominence both for his political career and subsequent legal troubles involving federal corruption charges.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32d7ef5cc819084cfeb1a3e39d3cc completed April 18, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f51d93081909ede0adcf8e604d4 completed May 10, 2026, 9:26 a.m.
NEDg Description generation batch_6a004fb5c28c81909da3d7b9b5c2be72 completed May 10, 2026, 9:28 a.m.
NED2 Entity disambiguation (via description) batch_6a00504d177c8190b4a4b4202d0167bb completed May 10, 2026, 9:30 a.m.
Created at: April 10, 2026, 5:10 a.m.