Triple

T10688651
Position Surface form Disambiguated ID Type / Status
Subject Knokke-Heist E251947 entity
Predicate borderedBy P224 FINISHED
Object Sluis E107638 NE FINISHED

How this triple was built (2 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: Sluis | Statement: [Knokke-Heist, borderedBy, Sluis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sluis
Context triple: [Knokke-Heist, borderedBy, Sluis]
  • A. Sluis chosen
    Sluis is a historic municipality and town in the southwestern Dutch province of Zeeland, near the Belgian border.
  • B. Torensluis
    Torensluis is one of Amsterdam’s oldest and widest stone bridges, notable for its historic architecture and remnants of a former tower and prison cells.
  • C. Maassluis
    Maassluis is a historic port town in the province of South Holland in the Netherlands, situated along the Nieuwe Waterweg west of Rotterdam.
  • D. Oranjesluizen
    Oranjesluizen is a complex of navigation locks and water management structures in Amsterdam that regulates water levels and access between the IJ/Markermeer and the city’s waterways.
  • E. Onderdendam
    Onderdendam is a small historic village in the Dutch province of Groningen, known for its canals, bridges, and traditional architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa5bd7c08190a816e733b4045c23 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fd1aef888190ba92474af3a49e36 completed April 9, 2026, 1:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d9889d1f988190938be54771161b00 completed April 10, 2026, 11:32 p.m.
Created at: April 8, 2026, 9:11 p.m.