Triple

T4684802
Position Surface form Disambiguated ID Type / Status
Subject Battle of Saucourt-en-Vimeu E103893 entity
Predicate location P40 FINISHED
Object Vimeu
Vimeu is a historical region in northern France, known for its medieval significance and as the site of the Battle of Saucourt-en-Vimeu.
 E460549 NE FINISHED

How this triple was built (4 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: Vimeu | Statement: [Battle of Saucourt-en-Vimeu, location, Vimeu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vimeu
Context triple: [Battle of Saucourt-en-Vimeu, location, Vimeu]
  • A. Viacha
    Viacha is a Bolivian city in the Altiplano region known for its industrial activity and proximity to La Paz.
  • B. Vimioso
    Vimioso is a municipality in northeastern Portugal known for its strong cultural ties to the Mirandese language and traditional rural heritage.
  • C. Vilca
    Vilca is a small Andean town in Peru known for its scenic highland landscapes, lagoons, and traditional rural culture within the Nor Yauyos-Cochas reserve.
  • D. Mvezo
    Mvezo is a small rural village in South Africa’s Eastern Cape best known as the birthplace of Nelson Mandela.
  • E. Kouri-Vini
    Kouri-Vini is a French-based Creole language historically spoken in Louisiana, particularly among Creole communities of African, Native American, and European descent.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vimeu
Triple: [Battle of Saucourt-en-Vimeu, location, Vimeu]
Generated description
Vimeu is a historical region in northern France, known for its medieval significance and as the site of the Battle of Saucourt-en-Vimeu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vimeu
Target entity description: Vimeu is a historical region in northern France, known for its medieval significance and as the site of the Battle of Saucourt-en-Vimeu.
  • A. Viacha
    Viacha is a Bolivian city in the Altiplano region known for its industrial activity and proximity to La Paz.
  • B. Vimioso
    Vimioso is a municipality in northeastern Portugal known for its strong cultural ties to the Mirandese language and traditional rural heritage.
  • C. Vilca
    Vilca is a small Andean town in Peru known for its scenic highland landscapes, lagoons, and traditional rural culture within the Nor Yauyos-Cochas reserve.
  • D. Mvezo
    Mvezo is a small rural village in South Africa’s Eastern Cape best known as the birthplace of Nelson Mandela.
  • E. Kouri-Vini
    Kouri-Vini is a French-based Creole language historically spoken in Louisiana, particularly among Creole communities of African, Native American, and European descent.
  • F. None of above. chosen

Provenance (5 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_69bd43debbf08190b4bc372e286ec234 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd63829b048190a2044de900ef7a69 completed March 20, 2026, 3:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69be03b07664819097d959fde1b0585b completed March 21, 2026, 2:34 a.m.
NEDg Description generation batch_69be04dc48b08190947cde715f87a4d0 completed March 21, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_69be05742e248190bb0e846189dfcfb5 completed March 21, 2026, 2:41 a.m.
Created at: March 20, 2026, 1:16 p.m.