Triple
T19377348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coulomb gap |
E484704
|
entity |
| Predicate | predictedBy |
P119
|
FINISHED |
| Object | Alexandre Efros |
—
|
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: Alexandre Efros | Statement: [Coulomb gap, predictedBy, Alexandre Efros]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alexandre Efros Context triple: [Coulomb gap, predictedBy, Alexandre Efros]
-
A.
Alexei Efros
chosen
Alexei Efros is a prominent computer scientist known for his influential work in computer vision and computational photography.
-
B.
Alexander Kolesnikov
Alexander Kolesnikov is a computer vision researcher best known as one of the creators of the Vision Transformer (ViT) architecture.
-
C.
Igor Osinkin
Igor Osinkin is a Russian football coach known for managing PFC Krylia Sovetov Samara in the Russian Premier League.
-
D.
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.
-
E.
Dmitry Shirkov
Dmitry Shirkov was a Soviet and Russian theoretical physicist known for his contributions to quantum field theory and renormalization group methods.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a5cfbf48190ac60e3ffa6baa263 |
completed | April 20, 2026, 12:21 p.m. |
Created at: April 10, 2026, 1:35 p.m.