Triple
T11172368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Kursk |
E264306
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Thomas Vinterberg |
E864900
|
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: Thomas Vinterberg | Statement: [The Kursk, director, Thomas Vinterberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Vinterberg Context triple: [The Kursk, director, Thomas Vinterberg]
-
A.
Thomas Vinterberg
chosen
Thomas Vinterberg is a Danish film director and screenwriter best known as a co-founder of the Dogme 95 movement and for acclaimed films such as "Festen" and "Another Round."
-
B.
Lars von Trier
Lars von Trier is a provocative Danish filmmaker known for his emotionally intense, stylistically experimental films and for co-founding the Dogme 95 movement.
-
C.
Bille August
Bille August is a Danish film director and screenwriter known for his acclaimed international dramas, including the Palme d'Or–winning "Pelle the Conqueror."
-
D.
Per Andersen
Per Andersen is a Norwegian neuroscientist renowned for his pioneering work on hippocampal circuitry and synaptic plasticity.
-
E.
Lars Bak
Lars Bak is a Danish computer scientist and software engineer best known for designing high-performance virtual machines and just-in-time compilers for languages such as Java and JavaScript.
- 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_69d6aa9dafac8190bd90d2c74f661aa7 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e89660208190b1d9e91529f5d246 |
completed | April 9, 2026, 5:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e483816af08190877f86ee52846581 |
completed | April 19, 2026, 7:25 a.m. |
Created at: April 8, 2026, 9:29 p.m.