Triple

T7623783
Position Surface form Disambiguated ID Type / Status
Subject Ollie Jackson Armstrong E172570 entity
Predicate givenName P17 FINISHED
Object Ollie
Ollie is a person whose full name is Ollie Jackson Armstrong.
 E675861 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: Ollie | Statement: [Ollie Jackson Armstrong, givenName, Ollie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ollie
Context triple: [Ollie Jackson Armstrong, givenName, Ollie]
  • A. McDuff
    McDuff is a surname most notably associated with Dusa McDuff, a prominent British-American mathematician known for her work in symplectic geometry.
  • B. Rodney Mullen
    Rodney Mullen is an American professional skateboarder widely regarded as the "Godfather of Street Skating" for inventing numerous foundational tricks and revolutionizing modern skateboarding.
  • C. Shaun White
    Shaun White is an American professional snowboarder and skateboarder, widely regarded as one of the greatest in his sport and a multi-time Olympic gold medalist.
  • D. Tony Hawks
    Tony Hawks is a British comedian and author best known for his radio and television comedy work, including frequent appearances on BBC panel shows.
  • E. Tony Hawk
    Tony Hawk is an American professional skateboarder widely regarded as one of the most influential figures in the history of the sport and a pioneer of modern vertical skateboarding.
  • 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: Ollie
Triple: [Ollie Jackson Armstrong, givenName, Ollie]
Generated description
Ollie is a person whose full name is Ollie Jackson Armstrong.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ollie
Target entity description: Ollie is a person whose full name is Ollie Jackson Armstrong.
  • A. McDuff
    McDuff is a surname most notably associated with Dusa McDuff, a prominent British-American mathematician known for her work in symplectic geometry.
  • B. Rodney Mullen
    Rodney Mullen is an American professional skateboarder widely regarded as the "Godfather of Street Skating" for inventing numerous foundational tricks and revolutionizing modern skateboarding.
  • C. Shaun White
    Shaun White is an American professional snowboarder and skateboarder, widely regarded as one of the greatest in his sport and a multi-time Olympic gold medalist.
  • D. Tony Hawks
    Tony Hawks is a British comedian and author best known for his radio and television comedy work, including frequent appearances on BBC panel shows.
  • E. Tony Hawk
    Tony Hawk is an American professional skateboarder widely regarded as one of the most influential figures in the history of the sport and a pioneer of modern vertical skateboarding.
  • 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_69c699506b308190826894dab1d9ea86 completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c6fa65309c8190b95b894c051b003d completed March 27, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8687b8c7481909e8d092b558fea84 completed March 28, 2026, 11:47 p.m.
NEDg Description generation batch_69c868dfc24c81908355f36323441bfd completed March 28, 2026, 11:48 p.m.
NED2 Entity disambiguation (via description) batch_69c8696a0d588190ab1e6d4c5c4bbb44 completed March 28, 2026, 11:51 p.m.
Created at: March 27, 2026, 3:56 p.m.