Triple

T4651099
Position Surface form Disambiguated ID Type / Status
Subject Transformer E102296 entity
Predicate introducedBy P513 FINISHED
Object Jakob Uszkoreit
Jakob Uszkoreit is a computer scientist and AI researcher best known as one of the co-authors of the seminal "Attention Is All You Need" paper that introduced the Transformer architecture.
E457854 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: Jakob Uszkoreit | Statement: [Transformer, introducedBy, Jakob Uszkoreit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jakob Uszkoreit
Context triple: [Transformer, introducedBy, Jakob Uszkoreit]
  • A. Ilya Sutskever
    Ilya Sutskever is a leading artificial intelligence researcher and co-founder of OpenAI, known for his pioneering work in deep learning and neural networks.
  • B. Nicolas Heess
    Nicolas Heess is a machine learning researcher known for his work in deep reinforcement learning, including contributions to algorithms such as Deep Deterministic Policy Gradient (DDPG).
  • C. Diederik P. Kingma
    Diederik P. Kingma is a machine learning researcher best known for co-developing the Adam optimization algorithm and the variational autoencoder (VAE) framework.
  • D. Tomas Mikolov
    Tomas Mikolov is a computer scientist and researcher best known for developing the word2vec algorithm and contributing foundational work to neural language models and distributed word representations.
  • E. Pascal Vincent
    Pascal Vincent is a Canadian professional ice hockey coach known for serving as head coach of the NHL’s Columbus Blue Jackets and for his extensive coaching career in junior and professional hockey.
  • 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: Jakob Uszkoreit
Triple: [Transformer, introducedBy, Jakob Uszkoreit]
Generated description
Jakob Uszkoreit is a computer scientist and AI researcher best known as one of the co-authors of the seminal "Attention Is All You Need" paper that introduced the Transformer architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jakob Uszkoreit
Target entity description: Jakob Uszkoreit is a computer scientist and AI researcher best known as one of the co-authors of the seminal "Attention Is All You Need" paper that introduced the Transformer architecture.
  • A. Ilya Sutskever
    Ilya Sutskever is a leading artificial intelligence researcher and co-founder of OpenAI, known for his pioneering work in deep learning and neural networks.
  • B. Nicolas Heess
    Nicolas Heess is a machine learning researcher known for his work in deep reinforcement learning, including contributions to algorithms such as Deep Deterministic Policy Gradient (DDPG).
  • C. Diederik P. Kingma
    Diederik P. Kingma is a machine learning researcher best known for co-developing the Adam optimization algorithm and the variational autoencoder (VAE) framework.
  • D. Tomas Mikolov
    Tomas Mikolov is a computer scientist and researcher best known for developing the word2vec algorithm and contributing foundational work to neural language models and distributed word representations.
  • E. Pascal Vincent
    Pascal Vincent is a Canadian professional ice hockey coach known for serving as head coach of the NHL’s Columbus Blue Jackets and for his extensive coaching career in junior and professional hockey.
  • 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_69bd43d71a308190afea7280841b0de8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd630343f88190954d19fcd18a5864 completed March 20, 2026, 3:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfae7636881908244b86cba1c66b7 completed March 21, 2026, 1:56 a.m.
NEDg Description generation batch_69bdfbc12acc8190b8116a6003abb3e3 completed March 21, 2026, 2 a.m.
NED2 Entity disambiguation (via description) batch_69bdfc44536c8190a71e52b0690a7570 completed March 21, 2026, 2:02 a.m.
Created at: March 20, 2026, 1:14 p.m.