Triple

T19424028
Position Surface form Disambiguated ID Type / Status
Subject De Rotterdam E485932 entity
Predicate client P27 FINISHED
Object City of Rotterdam 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: City of Rotterdam | Statement: [De Rotterdam, client, City of Rotterdam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of Rotterdam
Context triple: [De Rotterdam, client, City of Rotterdam]
  • A. Rotterdam chosen
    Rotterdam is a major Dutch port city known for having one of the world’s largest harbors and striking modern architecture.
  • B. Town of Rotterdam
    The Town of Rotterdam is a suburban municipality in Schenectady County, New York, known for its residential communities and proximity to the city of Schenectady.
  • C. Rotterdam city centre
    Rotterdam city centre is the vibrant commercial and cultural heart of Rotterdam, known for its modern architecture, shopping streets, and major transport hubs.
  • D. Dordrecht, Netherlands
    Dordrecht, Netherlands is a historic Dutch city in the province of South Holland, known for its medieval harbor, rich trading history, and well-preserved old town.
  • E. De Rotterdam
    De Rotterdam is a massive mixed-use high-rise complex in Rotterdam, Netherlands, designed by the architecture firm OMA and known for its stacked, shifting tower volumes along the Maas River.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63217bd2c81909e216e13aa4c487d completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.