Triple
T22262658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme region |
E550266
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Péronne |
—
|
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: Péronne | Statement: [Somme region, containsCity, Péronne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Péronne Context triple: [Somme region, containsCity, Péronne]
-
A.
Péronne
chosen
Péronne is a historic town in northern France known for its role in World War I and its location in the Somme department.
-
B.
Saint-Valery-sur-Somme
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.
-
C.
Landrecies
Landrecies is a small commune in northern France, historically part of the fortified border region of French Flanders.
-
D.
Ribemont-sur-Ancre
Ribemont-sur-Ancre is a commune in northern France’s Somme department, known for its riverside setting along the Ancre and its location in the historic Picardy region.
-
E.
Neufchâtel-sur-Aisne
Neufchâtel-sur-Aisne is a small commune in northern France situated along the Aisne River.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141b94a688190b17c55477993a745 |
completed | April 28, 2026, 11:24 p.m. |
Created at: April 16, 2026, 8:39 p.m.