Triple

T12813950
Position Surface form Disambiguated ID Type / Status
Subject Fehmarn Belt E306342 entity
Predicate separates P1175 FINISHED
Object island of Lolland E220370 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: island of Lolland | Statement: [Fehmarn Belt, separates, island of Lolland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: island of Lolland
Context triple: [Fehmarn Belt, separates, island of Lolland]
  • A. Lolland chosen
    Lolland is a large, predominantly agricultural island in southeastern Denmark known for its flat landscape and sugar beet production.
  • B. island of Zealand
    The island of Zealand is Denmark’s largest and most populous island, home to the capital city Copenhagen and a central hub of the country’s cultural, economic, and political life.
  • C. Tondern Island
    Tondern Island is a small island located within Lake Muskoka in Ontario, Canada, known for its scenic natural setting in the Muskoka cottage country region.
  • D. Langeland
    Langeland is a Danish island in the South Funen Archipelago, known for its rural landscapes, coastal scenery, and historical villages.
  • E. Mandø
    Mandø is a small Danish island in the Wadden Sea, known for its tidal causeway access, rich birdlife, and traditional marshland landscapes.
  • 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_69d7bdf46c448190b1faa55aaacb6317 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e9adcf08190a12801adcc613477 completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69b97ffd481909c540f52c781f63f completed May 3, 2026, 12:49 a.m.
Created at: April 9, 2026, 5:31 p.m.