Triple
T21414673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail Class 385 |
E528268
|
entity |
| Predicate | couplingType |
P21783
|
FINISHED |
| Object | Dellner |
—
|
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: Dellner | Statement: [British Rail Class 385, couplingType, Dellner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dellner Context triple: [British Rail Class 385, couplingType, Dellner]
-
A.
Dellner
chosen
Dellner is a company specializing in railway coupling and connection systems used on modern passenger and freight trains worldwide.
-
B.
Dollman
Dollman is a 1991 science fiction action film about a tough intergalactic cop who, after crash-landing on Earth, finds himself shrunken to 13 inches tall while continuing to battle criminals.
-
C.
Hauerland
Hauerland was a historical German-speaking enclave in central Slovakia, settled by Carpathian Germans in the Middle Ages.
-
D.
Klepper
Klepper is the surname of American comedian and television host Jordan Klepper, known for his work on political satire programs such as The Daily Show.
-
E.
Denner
Denner is a Swiss discount supermarket chain known for its low-price grocery offerings and widespread presence across Switzerland.
- 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_69e0c454c248819093425d1099101c09 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b2032fe48190907b282e2fffa2bd |
completed | April 22, 2026, 11:33 a.m. |
Created at: April 16, 2026, 5:45 p.m.