Triple
T17792735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicolas Heess |
E444207
|
entity |
| Predicate | hasCoAuthor |
P2389
|
FINISHED |
| Object | Martin Riedmiller |
—
|
NE NERFINISHED |
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: Martin Riedmiller | Statement: [Nicolas Heess, hasCoAuthor, Martin Riedmiller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Riedmiller Context triple: [Nicolas Heess, hasCoAuthor, Martin Riedmiller]
-
A.
Martin Riedmiller
chosen
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.
-
B.
Wolfram Burgard
Wolfram Burgard is a German computer scientist and roboticist known for his influential work in probabilistic robotics, autonomous navigation, and artificial intelligence.
-
C.
Jürgen Schmidhuber
Jürgen Schmidhuber is a German computer scientist and AI researcher best known for his pioneering work on neural networks and the co-invention of Long Short-Term Memory (LSTM) networks.
-
D.
Michael L. Littman
Michael L. Littman is an American computer scientist and professor known for his influential research in reinforcement learning, machine learning, and artificial intelligence.
-
E.
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.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4879859408190875835bd255e1185 |
completed | April 19, 2026, 7:43 a.m. |
Created at: April 10, 2026, 10:13 a.m.