Triple

T15592722
Position Surface form Disambiguated ID Type / Status
Subject Bar-le-Duc E374784 entity
Predicate hasPart P35 FINISHED
Object Ville Haute
Ville Haute is the historic upper town of Bar-le-Duc, known for its old architecture and elevated position overlooking the rest of the city.
E1165411 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: Ville Haute | Statement: [Bar-le-Duc, hasPart, Ville Haute]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ville Haute
Context triple: [Bar-le-Duc, hasPart, Ville Haute]
  • A. Ville Haute
    Ville Haute is the historic city-center district of Luxembourg City, known for its medieval fortifications, government buildings, and main shopping streets.
  • B. Chaumont
    Chaumont is a commune in northeastern France known as a local administrative and educational center, including hosting a campus of the University of Reims Champagne-Ardenne.
  • C. Leudeville
    Leudeville is a small commune in the Essonne department of the Île-de-France region in northern France.
  • D. Orleans
    Orleans is a coastal town on outer Cape Cod in Massachusetts known for its beaches, fishing, and role as a popular summer vacation destination.
  • E. Orleans
    Orleans is a white grape variety used in European wine production, historically cultivated in regions such as Germany and Central Europe.
  • 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: Ville Haute
Triple: [Bar-le-Duc, hasPart, Ville Haute]
Generated description
Ville Haute is the historic upper town of Bar-le-Duc, known for its old architecture and elevated position overlooking the rest of the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ville Haute
Target entity description: Ville Haute is the historic upper town of Bar-le-Duc, known for its old architecture and elevated position overlooking the rest of the city.
  • A. Ville Haute
    Ville Haute is the historic city-center district of Luxembourg City, known for its medieval fortifications, government buildings, and main shopping streets.
  • B. Chaumont
    Chaumont is a commune in northeastern France known as a local administrative and educational center, including hosting a campus of the University of Reims Champagne-Ardenne.
  • C. Leudeville
    Leudeville is a small commune in the Essonne department of the Île-de-France region in northern France.
  • D. Orleans
    Orleans is a coastal town on outer Cape Cod in Massachusetts known for its beaches, fishing, and role as a popular summer vacation destination.
  • E. Orleans
    Orleans is a white grape variety used in European wine production, historically cultivated in regions such as Germany and Central Europe.
  • 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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e5e43d48190a8fd367f13f1c7e1 completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c55fa248190b114a5b63560f87b completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff50020d748190be36f3c08df43e40 completed May 9, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff50a349688190ab7a18fa4460d86e completed May 9, 2026, 3:20 p.m.
Created at: April 10, 2026, 4:12 a.m.