Triple

T15621739
Position Surface form Disambiguated ID Type / Status
Subject Sneek E375572 entity
Predicate locatedOnWaterway P4361 FINISHED
Object Zwette
Zwette is a waterway in the Dutch city of Sneek, known for its role in local navigation and water management.
 E1167885 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: Zwette | Statement: [Sneek, locatedOnWaterway, Zwette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zwette
Context triple: [Sneek, locatedOnWaterway, Zwette]
  • A. Witte
    Witte is a surname most notably associated with Edwin E. Witte, an American economist often called the “father of Social Security” for his key role in shaping U.S. social welfare policy.
  • B. Blaak
    Blaak is a central transport hub and urban square in Rotterdam, known for its metro and train station near landmarks like the Cube Houses and Markthal.
  • C. Bleckede
    Bleckede is a small town in Lower Saxony, Germany, situated on the Elbe River and known for its historic architecture and natural surroundings.
  • D. Rood-witten
    Rood-witten is a popular nickname for PSV Eindhoven, referring to the club’s traditional red-and-white team colors.
  • E. Blaauw
    Blaauw is a Dutch surname most notably associated with Gerrit Blaauw, a pioneering computer architect involved in the design of early IBM systems.
  • 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: Zwette
Triple: [Sneek, locatedOnWaterway, Zwette]
Generated description
Zwette is a waterway in the Dutch city of Sneek, known for its role in local navigation and water management.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zwette
Target entity description: Zwette is a waterway in the Dutch city of Sneek, known for its role in local navigation and water management.
  • A. Witte
    Witte is a surname most notably associated with Edwin E. Witte, an American economist often called the “father of Social Security” for his key role in shaping U.S. social welfare policy.
  • B. Blaak
    Blaak is a central transport hub and urban square in Rotterdam, known for its metro and train station near landmarks like the Cube Houses and Markthal.
  • C. Bleckede
    Bleckede is a small town in Lower Saxony, Germany, situated on the Elbe River and known for its historic architecture and natural surroundings.
  • D. Rood-witten
    Rood-witten is a popular nickname for PSV Eindhoven, referring to the club’s traditional red-and-white team colors.
  • E. Blaauw
    Blaauw is a Dutch surname most notably associated with Gerrit Blaauw, a pioneering computer architect involved in the design of early IBM systems.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e9a95f08190b0013ba1428849d3 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f3da754819085a6bd9876b12c65 completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff605d94308190bccbfb4588f337e1 completed May 9, 2026, 4:27 p.m.
NED2 Entity disambiguation (via description) batch_69ff612340748190987e567e43460f62 completed May 9, 2026, 4:30 p.m.
Created at: April 10, 2026, 4:13 a.m.