Triple

T12086198
Position Surface form Disambiguated ID Type / Status
Subject Ghent City Hall E287812 entity
Predicate locatedAtStreet P959 FINISHED
Object Hoogpoort
Hoogpoort is a historic street in the center of Ghent, Belgium, known for its medieval architecture and important civic buildings.
E969026 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: Hoogpoort | Statement: [Ghent City Hall, locatedAtStreet, Hoogpoort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoogpoort
Context triple: [Ghent City Hall, locatedAtStreet, Hoogpoort]
  • A. Brouwersdam
    Brouwersdam is a major Dutch dam and causeway in the Rhine–Meuse–Scheldt delta, built as part of the Delta Works to protect the Netherlands from North Sea flooding while supporting road traffic and water management.
  • B. Woudenberg
    Woudenberg is a small Dutch municipality and town located in the central Netherlands.
  • C. Maasbracht
    Maasbracht is a town in the Dutch province of Limburg, known as an inland port and industrial center along the River Meuse.
  • D. Woudwetering
    Woudwetering is a Dutch waterway in South Holland that serves as an important local canal near the village of Woubrugge.
  • E. Everbeek
    Everbeek is a village in the municipality of Brakel in East Flanders, Belgium, known for its rural landscape and wooded surroundings.
  • 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: Hoogpoort
Triple: [Ghent City Hall, locatedAtStreet, Hoogpoort]
Generated description
Hoogpoort is a historic street in the center of Ghent, Belgium, known for its medieval architecture and important civic buildings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hoogpoort
Target entity description: Hoogpoort is a historic street in the center of Ghent, Belgium, known for its medieval architecture and important civic buildings.
  • A. Brouwersdam
    Brouwersdam is a major Dutch dam and causeway in the Rhine–Meuse–Scheldt delta, built as part of the Delta Works to protect the Netherlands from North Sea flooding while supporting road traffic and water management.
  • B. Woudenberg
    Woudenberg is a small Dutch municipality and town located in the central Netherlands.
  • C. Maasbracht
    Maasbracht is a town in the Dutch province of Limburg, known as an inland port and industrial center along the River Meuse.
  • D. Woudwetering
    Woudwetering is a Dutch waterway in South Holland that serves as an important local canal near the village of Woubrugge.
  • E. Everbeek
    Everbeek is a village in the municipality of Brakel in East Flanders, Belgium, known for its rural landscape and wooded surroundings.
  • 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_69d6ab4964708190850585628b287b0c completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d91514c78c8190bc1cd569e524e8b4 completed April 10, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a6d74888190aab150f1ceb2e9f1 completed May 2, 2026, 2:30 p.m.
NEDg Description generation batch_69f60bda16e48190af8abc0aa8ef41f0 completed May 2, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69f60cd1668881908f43d895fcfba0aa completed May 2, 2026, 2:40 p.m.
Created at: April 8, 2026, 9:48 p.m.