Triple

T15534574
Position Surface form Disambiguated ID Type / Status
Subject Cosmos E370308 entity
Predicate foundedBy P104 FINISHED
Object Jae Kwon
Jae Kwon is a software engineer and entrepreneur best known as the co-founder and original architect of the Cosmos blockchain ecosystem.
E1162436 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: Jae Kwon | Statement: [Cosmos, foundedBy, Jae Kwon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jae Kwon
Context triple: [Cosmos, foundedBy, Jae Kwon]
  • A. Taewan Kwan
    Taewan Kwan is a stage actor known for playing the character Lady Thiang in theatrical productions of "The King and I."
  • B. Jung Kim
    Jung Kim is the charismatic and quick-witted convenience store manager and son in the Canadian sitcom "Kim's Convenience."
  • C. Peter Sohn
    Peter Sohn is an American animator, voice actor, and film director at Pixar known for his work on projects like "Ratatouille," "The Good Dinosaur," and "Elemental."
  • D. Il-woo Jung
    Il-woo Jung is a Korean individual notable enough to be recognized as a prominent bearer of the surname Jung.
  • E. Lee Tae-hun
    Lee Tae-hun is a South Korean film producer known for his work on the international release of the science fiction thriller "Snowpiercer."
  • 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: Jae Kwon
Triple: [Cosmos, foundedBy, Jae Kwon]
Generated description
Jae Kwon is a software engineer and entrepreneur best known as the co-founder and original architect of the Cosmos blockchain ecosystem.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jae Kwon
Target entity description: Jae Kwon is a software engineer and entrepreneur best known as the co-founder and original architect of the Cosmos blockchain ecosystem.
  • A. Taewan Kwan
    Taewan Kwan is a stage actor known for playing the character Lady Thiang in theatrical productions of "The King and I."
  • B. Jung Kim
    Jung Kim is the charismatic and quick-witted convenience store manager and son in the Canadian sitcom "Kim's Convenience."
  • C. Peter Sohn
    Peter Sohn is an American animator, voice actor, and film director at Pixar known for his work on projects like "Ratatouille," "The Good Dinosaur," and "Elemental."
  • D. Il-woo Jung
    Il-woo Jung is a Korean individual notable enough to be recognized as a prominent bearer of the surname Jung.
  • E. Lee Tae-hun
    Lee Tae-hun is a South Korean film producer known for his work on the international release of the science fiction thriller "Snowpiercer."
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0442e327c8190b4b879c8a3cd38e3 completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d605b908190a18c63142c8bb854 completed May 9, 2026, 1:57 p.m.
NEDg Description generation batch_69ff3f59213c8190a9c98350225b5151 completed May 9, 2026, 2:06 p.m.
NED2 Entity disambiguation (via description) batch_69ff3ff96a6c8190a4c9f20dabc86cef completed May 9, 2026, 2:08 p.m.
Created at: April 10, 2026, 4:06 a.m.