Triple

T15693565
Position Surface form Disambiguated ID Type / Status
Subject Rubbestadneset E380396 entity
Predicate hasCompany P1287 FINISHED
Object Wärtsilä Norway E520635 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: Wärtsilä Norway | Statement: [Rubbestadneset, hasCompany, Wärtsilä Norway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wärtsilä Norway
Context triple: [Rubbestadneset, hasCompany, Wärtsilä Norway]
  • A. Wärtsilä chosen
    Wärtsilä is a Finnish technology company best known for manufacturing marine and energy power solutions, including ship engines and specialized vessels.
  • B. Wilhelmsen
    Wilhelmsen is a surname most prominently associated with the Norwegian global maritime industry group Wilh. Wilhelmsen Holding ASA.
  • C. Kongsberg Maritime
    Kongsberg Maritime is a Norwegian company that develops and supplies advanced maritime technology and solutions for offshore, marine, and subsea industries worldwide.
  • D. Norse Atlantic ASA
    Norse Atlantic ASA is a Norwegian aviation company that owns and operates the low-cost long-haul carrier Norse Atlantic Airways, focusing primarily on transatlantic routes.
  • E. STX Europe
    STX Europe was a major European shipbuilding group known for constructing cruise ships, ferries, and offshore vessels at several historic yards across Northern and Western Europe.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f4f5a888190bd3681bcb9bbc02f completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6eed9a8c8190a57ffce61a27ec17 completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:44 a.m.