Triple

T6322525
Position Surface form Disambiguated ID Type / Status
Subject Leeuwarden E141776 entity
Predicate hasCanal P35 FINISHED
Object Harlingertrekvaart
Harlingertrekvaart is a historic canal in the Dutch province of Friesland that connects the city of Leeuwarden with the port town of Harlingen.
E585186 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: Harlingertrekvaart | Statement: [Leeuwarden, hasCanal, Harlingertrekvaart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harlingertrekvaart
Context triple: [Leeuwarden, hasCanal, Harlingertrekvaart]
  • A. Storvreten
    Storvreten is a residential locality within Botkyrka Municipality in the Stockholm County area of Sweden.
  • B. Heenweg
    Heenweg is a small village in the Dutch municipality of Westland in the province of South Holland, Netherlands.
  • C. Hareid
    Hareid is a coastal village and municipality in western Norway known for its maritime industries and scenic fjord landscape.
  • D. Driewegen
    Driewegen is a small village in the Dutch province of Zeeland, located within the municipality of Borsele.
  • E. Holthees
    Holthees is a small village in the Dutch province of North Brabant, known for its rural character and historic church.
  • 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: Harlingertrekvaart
Triple: [Leeuwarden, hasCanal, Harlingertrekvaart]
Generated description
Harlingertrekvaart is a historic canal in the Dutch province of Friesland that connects the city of Leeuwarden with the port town of Harlingen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harlingertrekvaart
Target entity description: Harlingertrekvaart is a historic canal in the Dutch province of Friesland that connects the city of Leeuwarden with the port town of Harlingen.
  • A. Storvreten
    Storvreten is a residential locality within Botkyrka Municipality in the Stockholm County area of Sweden.
  • B. Heenweg
    Heenweg is a small village in the Dutch municipality of Westland in the province of South Holland, Netherlands.
  • C. Hareid
    Hareid is a coastal village and municipality in western Norway known for its maritime industries and scenic fjord landscape.
  • D. Driewegen
    Driewegen is a small village in the Dutch province of Zeeland, located within the municipality of Borsele.
  • E. Holthees
    Holthees is a small village in the Dutch province of North Brabant, known for its rural character and historic church.
  • 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_69c008d13b8c8190be47d896eb735605 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c064e38f1c81909c7e90b520602bae completed March 22, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e48a8c5c819099f21fdff1ce43f3 completed March 27, 2026, 1:59 a.m.
NEDg Description generation batch_69c5f8b0e0e48190896cc2abc6b26b89 completed March 27, 2026, 3:25 a.m.
NED2 Entity disambiguation (via description) batch_69c5f92a87148190b3c38f312a4901a4 completed March 27, 2026, 3:27 a.m.
Created at: March 22, 2026, 4:29 p.m.