Triple
T9291162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme (department) |
E223520
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Doullens |
E417970
|
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: Doullens | Statement: [Somme (department), containsTown, Doullens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Doullens Context triple: [Somme (department), containsTown, Doullens]
-
A.
Doullens
chosen
Doullens is a historic commune in northern France known for its medieval citadel and role as a strategic military and administrative center in the Somme department.
-
B.
Noyelles-Godault
Noyelles-Godault is a commune in the Pas-de-Calais department in northern France, historically associated with coal mining and known as the birthplace of French communist leader Maurice Thorez.
-
C.
Wattrelos
Wattrelos is a commune in northern France near the Belgian border, known historically for its textile industry and cross-border cultural ties.
-
D.
Creil
Creil is a commuter town in northern France’s Oise department, known as a regional rail hub connecting Paris with Picardy via major train and RER lines.
-
E.
Lillebonne
Lillebonne is a historic town in northern France’s Normandy region, known for its Roman archaeological remains and medieval 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_69ca8422ddf881908a3f8f876c9f53aa |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0865a7108190b807afd259980db2 |
completed | April 1, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14bcc15508190b54acd74d4d7c911 |
completed | April 4, 2026, 5:35 p.m. |
Created at: March 30, 2026, 7:35 p.m.