Triple

T15361053
Position Surface form Disambiguated ID Type / Status
Subject Olivier Bousquet E367288 entity
Predicate hasAcademicAdvisor P167 FINISHED
Object Bernhard Schölkopf E1115575 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: Bernhard Schölkopf | Statement: [Olivier Bousquet, hasAcademicAdvisor, Bernhard Schölkopf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernhard Schölkopf
Context triple: [Olivier Bousquet, hasAcademicAdvisor, Bernhard Schölkopf]
  • A. Bernhard Schölkopf chosen
    Bernhard Schölkopf is a leading German machine learning researcher known for his foundational work in kernel methods and causal inference, and for helping establish the Max Planck Institute for Intelligent Systems as a major center for AI research.
  • B. Thore Graepel
    Thore Graepel is a German computer scientist and machine learning researcher known for his work at DeepMind on game-playing AI systems and reinforcement learning.
  • C. Max Welling
    Max Welling is a prominent machine learning researcher known for foundational contributions to probabilistic deep learning and Bayesian inference, including co-developing variational autoencoders.
  • D. Martin Riedmiller
    Martin Riedmiller is a German computer scientist and pioneer in deep reinforcement learning, known for his influential work on neural-network-based control and contributions to landmark deep RL systems.
  • E. 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.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e4607408190ab281a7f7a8012d3 completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b4a181c8190bffc1ac1a86e215d completed May 9, 2026, 10:24 a.m.
Created at: April 10, 2026, 3:18 a.m.