Triple

T6155229
Position Surface form Disambiguated ID Type / Status
Subject Mariehamn E137303 entity
Predicate locatedOnIsland P970 FINISHED
Object Fasta Åland E23094 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: Fasta Åland | Statement: [Mariehamn, locatedOnIsland, Fasta Åland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fasta Åland
Context triple: [Mariehamn, locatedOnIsland, Fasta Åland]
  • A. Åland Islands chosen
    The Åland Islands are an autonomous, Swedish-speaking archipelago region of Finland known for their strategic location in the Baltic Sea and extensive self-governance.
  • B. Aland
    Aland is a surname most notably associated with German biblical scholar Barbara Aland.
  • C. Fårö
    Fårö is a small Baltic Sea island north of Gotland in Sweden, known for its distinctive limestone rock formations, beaches, and as the longtime home and filming location of director Ingmar Bergman.
  • D. Öland
    Öland is Sweden’s second-largest island, known for its unique limestone plains, rich birdlife, and popular summer tourism along the Baltic Sea coast.
  • E. Lidingö
    Lidingö is a suburban island town in the Stockholm archipelago known for its affluent residential areas, natural landscapes, and proximity to Sweden’s capital.
  • 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_69c008a45d008190832a9e19f5d63406 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05d01ddb0819085b5f5338b86a25d completed March 22, 2026, 9:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f77b22f08190b756a7cd8159b961 completed March 27, 2026, 9:32 p.m.
Created at: March 22, 2026, 4:17 p.m.