Triple

T22401761
Position Surface form Disambiguated ID Type / Status
Subject Halligen Frisian E553777 entity
Predicate spokenIn P2266 FINISHED
Object Gröde 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: Gröde | Statement: [Halligen Frisian, spokenIn, Gröde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gröde
Context triple: [Halligen Frisian, spokenIn, Gröde]
  • A. Gröde chosen
    Gröde is a tiny, sparsely populated Hallig island in the North Frisian archipelago off the coast of Germany, known for its unique tidal landscape and traditional way of life.
  • B. Grødem
    Grødem is a coastal village in Randaberg municipality in Rogaland county, Norway, known for its residential areas and proximity to the city of Stavanger.
  • C. Grohote
    Grohote is the main village and administrative center of the Croatian island of Šolta in the Adriatic Sea.
  • D. Graslei
    Graslei is a historic quay along the Leie River in the center of Ghent, Belgium, renowned for its picturesque row of medieval guild houses and vibrant café culture.
  • E. Gruden
    Gruden is a surname most prominently associated with Jon Gruden, a former NFL head coach and television analyst.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b4a96c8190838f5dda21c4d853 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.