Triple

T16063699
Position Surface form Disambiguated ID Type / Status
Subject Sullivan Award E389676 entity
Predicate notableRecipient P108 FINISHED
Object Caeleb Dressel
Caeleb Dressel is an American competitive swimmer and multiple Olympic gold medalist known for his dominance in sprint freestyle and butterfly events.
E1192145 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: Caeleb Dressel | Statement: [Sullivan Award, notableRecipient, Caeleb Dressel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caeleb Dressel
Context triple: [Sullivan Award, notableRecipient, Caeleb Dressel]
  • A. Jon Ledecky
    Jon Ledecky is an American businessman and investor best known as a co-owner of the NHL’s New York Islanders.
  • B. Katie Ledecky
    Katie Ledecky is an American freestyle swimmer and multiple-time Olympic and world champion widely regarded as one of the greatest female swimmers in history.
  • C. Jared Tallent
    Jared Tallent is an Australian race walker and Olympic champion best known for winning multiple Olympic and World Championship medals in the 20 km and 50 km walk events.
  • D. Lilly King
    Lilly King is an American breaststroke specialist and multiple Olympic gold medalist known for her dominance and outspoken stance against doping in swimming.
  • E. Rob Dressel
    Rob Dressel is a cinematographer best known for his work on the animated film "Big Hero 6."
  • 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: Caeleb Dressel
Triple: [Sullivan Award, notableRecipient, Caeleb Dressel]
Generated description
Caeleb Dressel is an American competitive swimmer and multiple Olympic gold medalist known for his dominance in sprint freestyle and butterfly events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Caeleb Dressel
Target entity description: Caeleb Dressel is an American competitive swimmer and multiple Olympic gold medalist known for his dominance in sprint freestyle and butterfly events.
  • A. Jon Ledecky
    Jon Ledecky is an American businessman and investor best known as a co-owner of the NHL’s New York Islanders.
  • B. Katie Ledecky
    Katie Ledecky is an American freestyle swimmer and multiple-time Olympic and world champion widely regarded as one of the greatest female swimmers in history.
  • C. Jared Tallent
    Jared Tallent is an Australian race walker and Olympic champion best known for winning multiple Olympic and World Championship medals in the 20 km and 50 km walk events.
  • D. Lilly King
    Lilly King is an American breaststroke specialist and multiple Olympic gold medalist known for her dominance and outspoken stance against doping in swimming.
  • E. Rob Dressel
    Rob Dressel is a cinematographer best known for his work on the animated film "Big Hero 6."
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837b048881908326739bbede756f completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe47ca9748190be24a490c3cf0e8c completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe50986b4819095bb9cd568fcf972 completed May 10, 2026, 1:53 a.m.
NED2 Entity disambiguation (via description) batch_69ffe56441b881909e3a97331e3821d2 completed May 10, 2026, 1:54 a.m.
Created at: April 10, 2026, 4:57 a.m.