Triple
T22262662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somme region |
E550266
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Fricourt |
E923193
|
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: Fricourt | Statement: [Somme region, containsTown, Fricourt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fricourt Context triple: [Somme region, containsTown, Fricourt]
-
A.
Fricourt
chosen
Fricourt is a village in the Somme department of northern France, notable for its World War I battlefields and military cemeteries.
-
B.
Voujeaucourt
Voujeaucourt is a commune in eastern France’s Bourgogne-Franche-Comté region, situated near Montbéliard in the Doubs department.
-
C.
Quesnoy-sur-Deûle
Quesnoy-sur-Deûle is a commune in northern France situated along the Deûle River within the Lille metropolitan area.
-
D.
Crépy-en-Valois
Crépy-en-Valois is a commune in the Oise department of northern France, known for its historic medieval center and role as a regional rail terminus.
-
E.
Bazentin
Bazentin is a commune in northern France notable as the birthplace of the pioneering evolutionary biologist Jean-Baptiste Lamarck.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141b94a688190b17c55477993a745 |
completed | April 28, 2026, 11:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ab66a08848190ac34b6af7a116f49 |
completed | May 18, 2026, 6:49 a.m. |
Created at: April 16, 2026, 8:39 p.m.