Triple

T4912452
Position Surface form Disambiguated ID Type / Status
Subject Uppland E110264 entity
Predicate borders P224 FINISHED
Object Gästrikland E178285 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: Gästrikland | Statement: [Uppland, borders, Gästrikland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gästrikland
Context triple: [Uppland, borders, Gästrikland]
  • A. Gästrikland chosen
    Gästrikland is a historical province in east-central Sweden known for its forests, ironworking heritage, and coastal location along the Gulf of Bothnia.
  • B. 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.
  • C. Lovön Island
    Lovön Island is an island in Lake Mälaren near Stockholm, Sweden, best known as the site of the UNESCO-listed Drottningholm Palace and its historic royal grounds.
  • D. Utö
    Utö is a Swedish island in the Stockholm archipelago known for its historic iron ore mines, scenic nature, and popular summer tourism.
  • E. Skaland
    Skaland is a small coastal village on the island of Senja in northern Norway, known for its scenic fjord landscape and proximity to rugged mountains.
  • 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_69bd44132b94819088522d92beaadc78 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6e9c32148190a940a3733ecd1898 completed March 20, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6fe7a0f48190b666202a97b32c7d completed March 21, 2026, 10:16 a.m.
Created at: March 20, 2026, 1:29 p.m.