Triple

T21376282
Position Surface form Disambiguated ID Type / Status
Subject Soisy-sur-Seine E527212 entity
Predicate hasDemonym P191 FINISHED
Object Soiséens
Soiséens are the inhabitants of the French commune of Soisy-sur-Seine in the Île-de-France region.
E1485731 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: Soiséens | Statement: [Soisy-sur-Seine, hasDemonym, Soiséens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soiséens
Context triple: [Soisy-sur-Seine, hasDemonym, Soiséens]
  • A. Saintois
    A Saintois is a resident or native of the coastal commune of Saintes-Maries-de-la-Mer in southern France.
  • B. Bresse
    Bresse is a historical region in eastern France known for its rich agricultural land, distinctive culinary traditions, and cultural ties to the Franco-Provençal linguistic area.
  • C. Semur-en-Auxois
    Semur-en-Auxois is a picturesque medieval hilltop town in the Côte-d'Or department of eastern France, known for its well-preserved ramparts and historic architecture.
  • D. Levensoises
    Levensoises are the female inhabitants or natives of Levens, a commune in the Alpes-Maritimes department in southeastern France.
  • E. Cuiseaux
    Cuiseaux is a small commune in eastern France, notable as the birthplace of the painter Édouard Vuillard.
  • 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: Soiséens
Triple: [Soisy-sur-Seine, hasDemonym, Soiséens]
Generated description
Soiséens are the inhabitants of the French commune of Soisy-sur-Seine in the Île-de-France region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Soiséens
Target entity description: Soiséens are the inhabitants of the French commune of Soisy-sur-Seine in the Île-de-France region.
  • A. Saintois
    A Saintois is a resident or native of the coastal commune of Saintes-Maries-de-la-Mer in southern France.
  • B. Bresse
    Bresse is a historical region in eastern France known for its rich agricultural land, distinctive culinary traditions, and cultural ties to the Franco-Provençal linguistic area.
  • C. Semur-en-Auxois
    Semur-en-Auxois is a picturesque medieval hilltop town in the Côte-d'Or department of eastern France, known for its well-preserved ramparts and historic architecture.
  • D. Levensoises
    Levensoises are the female inhabitants or natives of Levens, a commune in the Alpes-Maritimes department in southeastern France.
  • E. Cuiseaux
    Cuiseaux is a small commune in eastern France, notable as the birthplace of the painter Édouard Vuillard.
  • 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_69e0b51e80808190ba5cb05667af02a9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69ee62c9494081909efa74e189454dc6 completed April 26, 2026, 7:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a09c8f0f84c8190b8cf96aa3aa59cbf completed May 17, 2026, 1:56 p.m.
NEDg Description generation batch_6a09ccd6cf9c81909267e6c6e24c1499 completed May 17, 2026, 2:12 p.m.
NED2 Entity disambiguation (via description) batch_6a09cd669028819097c48056997a0a59 completed May 17, 2026, 2:15 p.m.
Created at: April 16, 2026, 5:11 p.m.