Triple

T13543954
Position Surface form Disambiguated ID Type / Status
Subject De Bilt E323463 entity
Predicate contains P35 FINISHED
Object Maartensdijk
Maartensdijk is a village in the Dutch province of Utrecht that forms part of the municipality of De Bilt.
E1046444 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: Maartensdijk | Statement: [De Bilt, contains, Maartensdijk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maartensdijk
Context triple: [De Bilt, contains, Maartensdijk]
  • A. Monnickendam
    Monnickendam is a historic fishing town in North Holland, Netherlands, known for its well-preserved old harbor and traditional Dutch architecture.
  • B. Drecht
    Drecht is a lesser-known Dutch river whose waters help form the Amstel through their confluence.
  • C. Oud-Waterschei
    Oud-Waterschei is a neighborhood of the Belgian city of Genk, historically known for its coal mining heritage and associated garden city architecture.
  • D. Strandvliet
    Strandvliet is a metro station in Amsterdam that serves passengers on the city's rapid transit network.
  • E. Zuidwolde
    Zuidwolde is a village in the Dutch province of Drenthe that serves as the administrative center of the municipality of De Wolden.
  • 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: Maartensdijk
Triple: [De Bilt, contains, Maartensdijk]
Generated description
Maartensdijk is a village in the Dutch province of Utrecht that forms part of the municipality of De Bilt.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maartensdijk
Target entity description: Maartensdijk is a village in the Dutch province of Utrecht that forms part of the municipality of De Bilt.
  • A. Monnickendam
    Monnickendam is a historic fishing town in North Holland, Netherlands, known for its well-preserved old harbor and traditional Dutch architecture.
  • B. Drecht
    Drecht is a lesser-known Dutch river whose waters help form the Amstel through their confluence.
  • C. Oud-Waterschei
    Oud-Waterschei is a neighborhood of the Belgian city of Genk, historically known for its coal mining heritage and associated garden city architecture.
  • D. Strandvliet
    Strandvliet is a metro station in Amsterdam that serves passengers on the city's rapid transit network.
  • E. Zuidwolde
    Zuidwolde is a village in the Dutch province of Drenthe that serves as the administrative center of the municipality of De Wolden.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafda36248190acabde65a88c5471 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75da094288190aff108b006c3da1f completed May 3, 2026, 2:37 p.m.
NEDg Description generation batch_69f75f2c645481909c3e5ecdd239965d completed May 3, 2026, 2:43 p.m.
NED2 Entity disambiguation (via description) batch_69f75f8e9b608190830ab942098a798c completed May 3, 2026, 2:45 p.m.
Created at: April 9, 2026, 9:45 p.m.