Triple
T3542918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Léon Bottou |
E74927
|
entity |
| Predicate | hasAcademicAdvisor |
P167
|
FINISHED |
| Object |
Vladimir Vapnik
Vladimir Vapnik is a pioneering computer scientist and statistician best known as a co-inventor of support vector machines and a founder of statistical learning theory.
|
E367287
|
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: Vladimir Vapnik | Statement: [Léon Bottou, hasAcademicAdvisor, Vladimir Vapnik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vladimir Vapnik Context triple: [Léon Bottou, hasAcademicAdvisor, Vladimir Vapnik]
-
A.
Léon Bottou
Léon Bottou is a French computer scientist known for his influential work in machine learning and neural networks, including key contributions to the development of the LeNet convolutional network.
-
B.
Gregory Piatetsky-Shapiro
Gregory Piatetsky-Shapiro is a pioneering computer scientist and data mining expert best known as the founder of the KDD (Knowledge Discovery and Data Mining) conferences and the KDnuggets data science community.
-
C.
Emanuel Parzen
Emanuel Parzen was an American statistician renowned for pioneering kernel density estimation, particularly through the development of the Parzen window method.
-
D.
Michael P. Kearns
Michael P. Kearns is an American politician from New York who has served in various local and state offices, including roles in the New York State Assembly and Erie County government.
-
E.
Ruslan Salakhutdinov
Ruslan Salakhutdinov is a prominent machine learning researcher known for his contributions to deep learning and probabilistic graphical models, and for serving as Director of AI Research at Apple and a professor at Carnegie Mellon University.
- 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: Vladimir Vapnik Triple: [Léon Bottou, hasAcademicAdvisor, Vladimir Vapnik]
Generated description
Vladimir Vapnik is a pioneering computer scientist and statistician best known as a co-inventor of support vector machines and a founder of statistical learning theory.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vladimir Vapnik Target entity description: Vladimir Vapnik is a pioneering computer scientist and statistician best known as a co-inventor of support vector machines and a founder of statistical learning theory.
-
A.
Léon Bottou
Léon Bottou is a French computer scientist known for his influential work in machine learning and neural networks, including key contributions to the development of the LeNet convolutional network.
-
B.
Gregory Piatetsky-Shapiro
Gregory Piatetsky-Shapiro is a pioneering computer scientist and data mining expert best known as the founder of the KDD (Knowledge Discovery and Data Mining) conferences and the KDnuggets data science community.
-
C.
Emanuel Parzen
Emanuel Parzen was an American statistician renowned for pioneering kernel density estimation, particularly through the development of the Parzen window method.
-
D.
Michael P. Kearns
Michael P. Kearns is an American politician from New York who has served in various local and state offices, including roles in the New York State Assembly and Erie County government.
-
E.
Ruslan Salakhutdinov
Ruslan Salakhutdinov is a prominent machine learning researcher known for his contributions to deep learning and probabilistic graphical models, and for serving as Director of AI Research at Apple and a professor at Carnegie Mellon University.
- 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_69ad85d274cc8190ab59c97298a1cfbf |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbf752dd481909226044ffe595338 |
completed | March 8, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38bdd0cb4819086119b54c2708850 |
completed | March 13, 2026, 4 a.m. |
| NEDg | Description generation | batch_69b38cb6a2188190b68f4903144a0e51 |
completed | March 13, 2026, 4:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b39062a10c8190bc227c02cf4f3ab1 |
completed | March 13, 2026, 4:19 a.m. |
Created at: March 8, 2026, 3:20 p.m.