Triple

T480905
Position Surface form Disambiguated ID Type / Status
Subject Khan Academy E9163 entity
Predicate foundedBy P104 FINISHED
Object Sal Khan
Sal Khan is an American educator and entrepreneur best known as the founder of the online learning platform Khan Academy, which offers free educational resources worldwide.
E59930 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: Sal Khan | Statement: [Khan Academy, foundedBy, Sal Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sal Khan
Context triple: [Khan Academy, foundedBy, Sal Khan]
  • A. Jawed Karim
    Jawed Karim is a German-American computer scientist and entrepreneur best known as a co-founder of YouTube and the uploader of its first video.
  • B. Anant Agarwal
    Anant Agarwal is a computer scientist and MIT professor best known as the founding CEO of edX, a major online learning platform.
  • C. Sergey Brin
    Sergey Brin is a computer scientist and internet entrepreneur best known as the co-founder of Google.
  • D. Chad Hurley
    Chad Hurley is an American entrepreneur and technologist best known as a co-founder and former CEO of the video-sharing platform YouTube.
  • E. Parag Agrawal
    Parag Agrawal is an Indian-American technology executive and computer scientist best known for serving as the chief executive officer of Twitter.
  • 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: Sal Khan
Triple: [Khan Academy, foundedBy, Sal Khan]
Generated description
Sal Khan is an American educator and entrepreneur best known as the founder of the online learning platform Khan Academy, which offers free educational resources worldwide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sal Khan
Target entity description: Sal Khan is an American educator and entrepreneur best known as the founder of the online learning platform Khan Academy, which offers free educational resources worldwide.
  • A. Jawed Karim
    Jawed Karim is a German-American computer scientist and entrepreneur best known as a co-founder of YouTube and the uploader of its first video.
  • B. Anant Agarwal
    Anant Agarwal is a computer scientist and MIT professor best known as the founding CEO of edX, a major online learning platform.
  • C. Sergey Brin
    Sergey Brin is a computer scientist and internet entrepreneur best known as the co-founder of Google.
  • D. Chad Hurley
    Chad Hurley is an American entrepreneur and technologist best known as a co-founder and former CEO of the video-sharing platform YouTube.
  • E. Parag Agrawal
    Parag Agrawal is an Indian-American technology executive and computer scientist best known for serving as the chief executive officer of Twitter.
  • 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_69a2e7ff81708190b0507a24a997232c completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f058ebe48190aaa0a829b21f75fa completed Feb. 28, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69a46c60a02081908bbb7b4ee12903a6 completed March 1, 2026, 4:42 p.m.
NEDg Description generation batch_69a46cc070f48190a58b65b67efa25de completed March 1, 2026, 4:43 p.m.
NED2 Entity disambiguation (via description) batch_69a46d2002d8819086691b73f8fbaae2 completed March 1, 2026, 4:45 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.