Triple

T1512436
Position Surface form Disambiguated ID Type / Status
Subject Antwerp E32042 entity
Predicate hasDistrict P459 FINISHED
Object Borgerhout
Borgerhout is a densely populated, multicultural district of the Belgian city of Antwerp, known for its vibrant street life and diverse communities.
 E275226 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: Borgerhout | Statement: [Antwerp, hasDistrict, Borgerhout]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Borgerhout
Context triple: [Antwerp, hasDistrict, Borgerhout]
  • A. Roeselare
    Roeselare is a city in western Belgium known as an economic and commercial center in the province of West Flanders.
  • B. Vilvoorde
    Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
  • C. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • D. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • E. Hasselt
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • 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: Borgerhout
Triple: [Antwerp, hasDistrict, Borgerhout]
Generated description
Borgerhout is a densely populated, multicultural district of the Belgian city of Antwerp, known for its vibrant street life and diverse communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Borgerhout
Target entity description: Borgerhout is a densely populated, multicultural district of the Belgian city of Antwerp, known for its vibrant street life and diverse communities.
  • A. Roeselare
    Roeselare is a city in western Belgium known as an economic and commercial center in the province of West Flanders.
  • B. Vilvoorde
    Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
  • C. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • D. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • E. Hasselt
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • 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_69a885e8caf88190a5fbb6159ce87786 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a907d7cbf48190be40590a7f9fa1de completed March 5, 2026, 4:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b42bb888190a0b16e3a59eb1175 completed March 9, 2026, 8:19 p.m.
NEDg Description generation batch_69af50f642788190afd3663bd4d43ae4 completed March 9, 2026, 11 p.m.
NED2 Entity disambiguation (via description) batch_69af51ca7024819085f371a0ef85d9c2 completed March 9, 2026, 11:03 p.m.
Created at: March 4, 2026, 7:26 p.m.