Triple

T16469920
Position Surface form Disambiguated ID Type / Status
Subject Canton of Moreuil E400032 entity
Predicate containsCommune P15149 FINISHED
Object Fouquescourt
Fouquescourt is a small rural commune in northern France’s Somme department, characterized by its agricultural landscape and traditional Picard village setting.
E1216546 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: Fouquescourt | Statement: [Canton of Moreuil, containsCommune, Fouquescourt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fouquescourt
Context triple: [Canton of Moreuil, containsCommune, Fouquescourt]
  • A. Blignicourt
    Blignicourt is a small commune in the Aube department of north-central France.
  • B. Juvancourt
    Juvancourt is a small commune in the Aube department in north-central France.
  • C. Bois-de-Villers
    Bois-de-Villers is a village in the municipality of Jalhay in the Walloon region of Belgium, known for its rural setting in the Ardennes.
  • D. Beaucourt
    Beaucourt is a small French commune located in the northeastern region of Bourgogne-Franche-Comté near the Swiss border.
  • E. Morlaincourt
    Morlaincourt is a small commune in northeastern France, likely known locally for its rural character and proximity to the Yonne river’s headwaters.
  • 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: Fouquescourt
Triple: [Canton of Moreuil, containsCommune, Fouquescourt]
Generated description
Fouquescourt is a small rural commune in northern France’s Somme department, characterized by its agricultural landscape and traditional Picard village setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fouquescourt
Target entity description: Fouquescourt is a small rural commune in northern France’s Somme department, characterized by its agricultural landscape and traditional Picard village setting.
  • A. Blignicourt
    Blignicourt is a small commune in the Aube department of north-central France.
  • B. Juvancourt
    Juvancourt is a small commune in the Aube department in north-central France.
  • C. Bois-de-Villers
    Bois-de-Villers is a village in the municipality of Jalhay in the Walloon region of Belgium, known for its rural setting in the Ardennes.
  • D. Beaucourt
    Beaucourt is a small French commune located in the northeastern region of Bourgogne-Franche-Comté near the Swiss border.
  • E. Morlaincourt
    Morlaincourt is a small commune in northeastern France, likely known locally for its rural character and proximity to the Yonne river’s headwaters.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32dcfed6c8190b8dbe4b65b0ab817 completed April 18, 2026, 7:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00581c24508190b4888357828fed80 completed May 10, 2026, 10:04 a.m.
NEDg Description generation batch_6a00592562708190ae88f24fb34c7a02 completed May 10, 2026, 10:08 a.m.
NED2 Entity disambiguation (via description) batch_6a005a17fd648190b2c6843f47a9ee2c completed May 10, 2026, 10:12 a.m.
Created at: April 10, 2026, 5:11 a.m.