Triple

T13660280
Position Surface form Disambiguated ID Type / Status
Subject Beleg van Oostende E326976 entity
Predicate location P40 FINISHED
Object Oostende E128320 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: Oostende | Statement: [Beleg van Oostende, location, Oostende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oostende
Context triple: [Beleg van Oostende, location, Oostende]
  • A. Blankenberge
    Blankenberge is a Belgian coastal town on the North Sea known for its sandy beaches, seaside promenade, and tourism.
  • B. Wervik
    Wervik is a historic town and municipality in the Belgian province of West Flanders, situated along the river Lys near the French border.
  • C. Ostend chosen
    Ostend is a Belgian coastal city on the North Sea known for its beaches, port, and seaside tourism.
  • D. Ostend
    Ostend is a small residential and commercial settlement on Waiheke Island in New Zealand’s Hauraki Gulf.
  • E. Duinkerke
    Duinkerke is the Dutch name for Dunkirk, a historic port city in northern France known for its pivotal World War II evacuation.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc61f0d808190b1cd2a6ba0d930eb completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f794395618819094a7f0ffcf5d3fb6 completed May 3, 2026, 6:30 p.m.
Created at: April 9, 2026, 9:52 p.m.