Triple

T10995253
Position Surface form Disambiguated ID Type / Status
Subject Mike Sokolsky E259846 entity
Predicate coFounderOf P104 FINISHED
Object Udacity E11013 NE FINISHED

How this triple was built (2 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: Udacity | Statement: [Mike Sokolsky, coFounderOf, Udacity]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Udacity
Context triple: [Mike Sokolsky, coFounderOf, Udacity]
  • A. Udacity chosen
    Udacity is an online learning platform specializing in technology-focused courses and career-oriented "Nanodegree" programs developed in collaboration with industry partners.
  • B. Coursera
    Coursera is a major online learning platform that partners with universities and organizations worldwide to offer courses, professional certificates, and degree programs across a wide range of subjects.
  • C. Udemy
    Udemy is a global online learning platform that hosts a vast marketplace of video-based courses across diverse subjects for learners and professionals.
  • D. edX
    edX is a leading online learning platform founded by MIT and Harvard that offers university-level courses, professional certificates, and degree programs to learners worldwide.
  • E. Great Learning
    Great Learning is a foundational Confucian classic that outlines principles of moral self-cultivation and good governance.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d795d59ebc8190baff1f50bdc46c1b completed April 9, 2026, 12:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3452420c08190b9c91a9c8a807670 completed April 18, 2026, 8:47 a.m.
Created at: April 8, 2026, 9:24 p.m.