Triple
T8619240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Millbay Docks |
E204120
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Roscoff |
E636551
|
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: Roscoff | Statement: [Millbay Docks, connectsTo, Roscoff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roscoff Context triple: [Millbay Docks, connectsTo, Roscoff]
-
A.
Roscoff
chosen
Roscoff is a picturesque coastal town in Brittany, France, known for its historic port, thalassotherapy centers, and traditional onion-exporting heritage.
-
B.
Concarneau
Concarneau is a coastal town and fishing port in Brittany, France, known for its walled medieval "Ville Close" and maritime heritage.
-
C.
Morlaix
Morlaix is a historic town and port in the Finistère department of Brittany in northwestern France, known for its picturesque old center and impressive railway viaduct.
-
D.
Le Croisic
Le Croisic is a coastal town and popular seaside resort on the Atlantic coast of western France, known for its historic harbor and scenic peninsula.
-
E.
Le Moule
Le Moule is a coastal commune and former sugar port on the island of Grande-Terre in Guadeloupe, known for its surfing beaches and colonial-era heritage.
- 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_69ca832ceab8819096e4a9f546695079 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc471458f48190a6d8858f8074727d |
completed | March 31, 2026, 10:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebbd49cc8819093555edf5ff0acaa |
completed | April 2, 2026, 6:56 p.m. |
Created at: March 30, 2026, 6:26 p.m.