Triple

T21882875
Position Surface form Disambiguated ID Type / Status
Subject Waterland E540332 entity
Predicate containsSettlement P847 FINISHED
Object Marken 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: Marken | Statement: [Waterland, containsSettlement, Marken]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marken
Context triple: [Waterland, containsSettlement, Marken]
  • A. Marken chosen
    Marken is a small, picturesque former island village in the Netherlands known for its traditional wooden houses, fishing heritage, and distinctive cultural character.
  • B. Marca
    Marca is a leading Spanish national daily sports newspaper best known for its extensive football coverage and creation of awards such as the Pichichi Trophy.
  • C. Brandbu
    Brandbu is a village in Gran Municipality in Innlandet county, Norway, known as a local commercial and service center in the Hadeland district.
  • D. Dimension brand
    Dimension brand is a film and television production label best known for releasing genre and horror titles under the larger Dimension Films/Television umbrella.
  • E. Brand
    Brand is a key astronaut and scientist in the film "Interstellar," serving as one of the central figures in humanity's mission to find a new habitable world.
  • 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_69e0c479a98081908ce333853fdd4348 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f118e890088190aa3023c78a99a536 completed April 28, 2026, 8:30 p.m.
Created at: April 16, 2026, 7:05 p.m.