Triple

T18059857
Position Surface form Disambiguated ID Type / Status
Subject Kungstornen E432141 entity
Predicate hasPart P35 FINISHED
Object Norra Kungstornet 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: Norra Kungstornet | Statement: [Kungstornen, hasPart, Norra Kungstornet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norra Kungstornet
Context triple: [Kungstornen, hasPart, Norra Kungstornet]
  • A. Kungstornen chosen
    Kungstornen are a pair of early 20th-century twin skyscrapers in central Stockholm, considered among Sweden’s first high-rise office buildings and an iconic part of the city’s skyline.
  • B. Kungliga slottet
    Kungliga slottet is the official royal palace and primary residence of the Swedish monarch, located in Stockholm’s Old Town.
  • C. Karlatornet
    Karlatornet is a supertall skyscraper in Gothenburg, Sweden, known for being the country's tallest building and a prominent new landmark on the city's skyline.
  • D. Norrtull
    Norrtull is a major traffic junction and historical city gate area in northern central Stockholm, Sweden.
  • E. Nyköping Castle
    Nyköping Castle is a historic medieval fortress in the town of Nyköping, Sweden, notable as a royal residence and the site of several significant events in Swedish history.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c10583648190a161c58abf4853d5 completed April 19, 2026, 11:48 a.m.
Created at: April 10, 2026, 10:26 a.m.