Triple

T21517055
Position Surface form Disambiguated ID Type / Status
Subject Walrus-class submarine E530871 entity
Predicate builder P3143 FINISHED
Object Rotterdamsche Droogdok Maatschappij — NE NERFINISHED

How this triple was built (3 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: Rotterdamsche Droogdok Maatschappij | Statement: [Walrus-class submarine, builder, Rotterdamsche Droogdok Maatschappij]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rotterdamsche Droogdok Maatschappij
Context triple: [Walrus-class submarine, builder, Rotterdamsche Droogdok Maatschappij]
  • A. Nederlandsche Dok en Scheepsbouw Maatschappij
    Nederlandsche Dok en Scheepsbouw Maatschappij was a major Dutch shipbuilding and repair company based in Amsterdam, historically known for constructing and maintaining a wide range of commercial and naval vessels.
  • B. Boskalis
    Boskalis is a Dutch dredging and marine services company known for large-scale land reclamation, coastal engineering, and offshore infrastructure projects.
  • C. Koninklijke Nederlandsche Stoomboot-Maatschappij
    Koninklijke Nederlandsche Stoomboot-Maatschappij was a historic Dutch shipping company that played a major role in maritime trade and passenger transport from the 19th to the 20th century.
  • D. Knooppunt Zaandam
    Knooppunt Zaandam is a major motorway interchange in the Netherlands connecting the A10 ring road around Amsterdam with routes toward Zaandam and the surrounding region.
  • E. Royal Vopak
    Royal Vopak is a Dutch multinational tank storage company that specializes in storing and handling liquid bulk products such as chemicals, oil, gases, and biofuels at terminals worldwide.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rotterdamsche Droogdok Maatschappij
Target entity description: Rotterdamsche Droogdok Maatschappij was a major Dutch shipbuilding and repair company based in Rotterdam, known for constructing naval vessels including submarines.
  • A. Nederlandsche Dok en Scheepsbouw Maatschappij
    Nederlandsche Dok en Scheepsbouw Maatschappij was a major Dutch shipbuilding and repair company based in Amsterdam, historically known for constructing and maintaining a wide range of commercial and naval vessels.
  • B. Boskalis
    Boskalis is a Dutch dredging and marine services company known for large-scale land reclamation, coastal engineering, and offshore infrastructure projects.
  • C. Koninklijke Nederlandsche Stoomboot-Maatschappij
    Koninklijke Nederlandsche Stoomboot-Maatschappij was a historic Dutch shipping company that played a major role in maritime trade and passenger transport from the 19th to the 20th century.
  • D. Knooppunt Zaandam
    Knooppunt Zaandam is a major motorway interchange in the Netherlands connecting the A10 ring road around Amsterdam with routes toward Zaandam and the surrounding region.
  • E. Royal Vopak
    Royal Vopak is a Dutch multinational tank storage company that specializes in storing and handling liquid bulk products such as chemicals, oil, gases, and biofuels at terminals worldwide.
  • F. None of above. chosen

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_69e0c45d95a081908e7962ad215da746 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee814278e08190a66d516bed0726b5 completed April 26, 2026, 9:18 p.m.
Created at: April 16, 2026, 6:25 p.m.