Triple
T15229279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme Bay |
E363955
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Saint-Valery-sur-Somme |
E798802
|
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: Saint-Valery-sur-Somme | Statement: [Somme Bay, near, Saint-Valery-sur-Somme]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Valery-sur-Somme Context triple: [Somme Bay, near, Saint-Valery-sur-Somme]
-
A.
Saint-Valery-sur-Somme
chosen
Saint-Valery-sur-Somme is a historic coastal town in northern France, known for its picturesque setting on the Baie de Somme and its well-preserved medieval architecture.
-
B.
Vaux-sur-Somme
Vaux-sur-Somme is a small commune in the Somme department of northern France, known for its association with World War I aviation history.
-
C.
Péronne
Péronne is a historic town in northern France known for its role in World War I and its location in the Somme department.
-
D.
Pont-Audemer
Pont-Audemer is a historic market town in northern France known for its picturesque canals and half-timbered houses, often called the "Norman Venice."
-
E.
Landrecies
Landrecies is a small commune in northern France, historically part of the fortified border region of French Flanders.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0078ccdf48190b34eabd9e24e45a1 |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fee5edca5c8190827788324a9e886d |
completed | May 9, 2026, 7:44 a.m. |
Created at: April 10, 2026, 3:12 a.m.