Triple

T23201586
Position Surface form Disambiguated ID Type / Status
Subject Hekelingen–Piershil ferry E580325 entity
Predicate river P165 FINISHED
Object Spui NE NERFINISHED

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: Spui | Statement: [Hekelingen–Piershil ferry, river, Spui]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spui
Context triple: [Hekelingen–Piershil ferry, river, Spui]
  • A. Spui
    Spui is a central square and tram hub in Amsterdam, Netherlands, known for its bookstores, cultural venues, and proximity to historic canals.
  • B. Spui chosen
    Spui is a small tidal river in South Holland, Netherlands, that branches off from the Oude Maas and plays a role in the region’s delta water system.
  • C. Bruinisse
    Bruinisse is a fishing village and tourist destination in the Dutch province of Zeeland, known for its mussel industry and location on the Grevelingen.
  • D. Merksplas
    Merksplas is a Belgian municipality in the province of Antwerp, historically known for its agricultural colony that formed part of the 19th-century social reform project called the Colonies of Benevolence.
  • E. Spreeau
    Spreeau is a small locality within the municipality of Grünheide (Mark) in the German state of Brandenburg.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24602ae1481908aaa6bc7ca493867 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f19079c44881909e8677921b08b931 completed April 29, 2026, 5 a.m.
Created at: April 17, 2026, 4:06 p.m.