Triple

T10343384
Position Surface form Disambiguated ID Type / Status
Subject Battle of Courcelette E243680 entity
Predicate theatre P671 FINISHED
Object Somme sector E550266 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: Somme sector | Statement: [Battle of Courcelette, theatre, Somme sector]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somme sector
Context triple: [Battle of Courcelette, theatre, Somme sector]
  • A. Yser Front
    The Yser Front was a key World War I defensive line in western Belgium where Belgian forces halted the German advance along the Yser River.
  • B. Somme, France
    Somme, France is a department in northern France best known as the site of major World War I battles, including the Battle of the Somme.
  • C. Somme region chosen
    The Somme region is an area in northern France historically significant as the site of major World War I battles, particularly the Battle of the Somme.
  • D. Aisne-Marne
    Aisne-Marne refers to a major World War I campaign and battlefield in France, notably associated with the Second Battle of the Marne.
  • E. Trench of Death
    Trench of Death is a preserved First World War front-line trench complex near Diksmuide in Belgium, maintained as a memorial and open-air museum commemorating the brutal trench warfare on the Yser Front.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e92105888190a08104deb9d0cf1c completed April 7, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75077dfbc81908de29aac1a3bb19f completed April 9, 2026, 7:08 a.m.
Created at: April 6, 2026, 11:55 a.m.