Triple
T9291148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme (department) |
E223520
|
entity |
| Predicate | subprefecture |
P9697
|
FINISHED |
| Object | Montdidier |
E451215
|
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: Montdidier | Statement: [Somme (department), subprefecture, Montdidier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Montdidier Context triple: [Somme (department), subprefecture, Montdidier]
-
A.
Montdidier
chosen
Montdidier is a small historic town in northern France, located in the Somme department of the Hauts-de-France region.
-
B.
Serigny
Serigny is a French given name historically associated with the colonial-era figure Serigny Le Moyne.
-
C.
Douaumont
Douaumont is a small commune in northeastern France best known for its World War I battlefield sites near Verdun, including major memorials and military cemeteries.
-
D.
Tournan
Tournan is a suburban town in the Île-de-France region of France that serves as an outer terminus for Paris’s RER commuter rail network.
-
E.
Remigny
Remigny is a small wine-producing village in the Burgundy region of eastern France, situated near the renowned appellation of Santenay.
- 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_69d12cc59610819090adf2b4c3f5cec3 |
completed | April 4, 2026, 3:22 p.m. |
Created at: March 30, 2026, 7:35 p.m.