Triple
T13959954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fire in Delft |
E335765
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Egbert van der Poel |
E67159
|
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: Egbert van der Poel | Statement: [Fire in Delft, creator, Egbert van der Poel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Egbert van der Poel Context triple: [Fire in Delft, creator, Egbert van der Poel]
-
A.
Egbert van der Poel
chosen
Egbert van der Poel was a 17th-century Dutch Golden Age painter known for his atmospheric depictions of fires, nocturnal scenes, and everyday life in and around Delft.
-
B.
Daan Wierstra
Daan Wierstra is a machine learning researcher known for his contributions to deep reinforcement learning, including co-authoring the influential Atari deep Q-network work at DeepMind.
-
C.
Maarten Baas
Maarten Baas is a Dutch designer and artist renowned for his conceptual, often playful furniture and installations that blur the boundaries between art and design.
-
D.
Marc de Jonge
Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
-
E.
Bart van Merriënboer
Bart van Merriënboer is a machine learning researcher known for his contributions to deep learning and neural sequence models, including work on RNN-based encoder–decoder architectures for machine translation.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e7b2f908190aa32f22298964746 |
completed | April 14, 2026, 12:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fba1d490048190b28cb44dd4ec46c4 |
completed | May 6, 2026, 8:17 p.m. |
Created at: April 9, 2026, 10:17 p.m.