Triple
T18994825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dover, Kent, England |
E464782
|
entity |
| Predicate | connectsToByFerry |
P1831
|
FINISHED |
| Object | Dunkirk, France |
—
|
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: Dunkirk, France | Statement: [Dover, Kent, England, connectsToByFerry, Dunkirk, France]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dunkirk, France Context triple: [Dover, Kent, England, connectsToByFerry, Dunkirk, France]
-
A.
Dunkirk, France
chosen
Dunkirk, France is a coastal city in northern France on the North Sea, historically renowned as the site of the World War II Dunkirk evacuation.
-
B.
Dunkirk, Kent
Dunkirk, Kent is a village in southeast England that forms part of the historic coastal confederation known as the Cinque Ports.
-
C.
Dieppe, Normandy, France
Dieppe is a historic port city on the English Channel in Normandy, northern France, known for its maritime heritage, pebble beach, and role in World War II.
-
D.
Dunkerque
Dunkerque is a coastal city and major port in northern France on the North Sea, near the Belgian border, known for its strategic role in World War II.
-
E.
Dunker
Dunker is the costumed racehorse mascot that represents Murray State University at its athletic events and campus activities.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d680dd2881908a72e732c6b25477 |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.