Triple

T19403619
Position Surface form Disambiguated ID Type / Status
Subject Tønsberg Fortress E485391 entity
Predicate hasPart P35 FINISHED
Object Slottsfjell Tower 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: Slottsfjell Tower | Statement: [Tønsberg Fortress, hasPart, Slottsfjell Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Slottsfjell Tower
Context triple: [Tønsberg Fortress, hasPart, Slottsfjell Tower]
  • A. Slottsfjell Tower chosen
    Slottsfjell Tower is a historic stone tower and prominent viewpoint in Tønsberg, Norway, commemorating the town’s medieval fortress and offering panoramic views of the surrounding area.
  • B. Notvik Tower
    Notvik Tower is a 19th-century coastal defensive tower that formed part of the Russian-built Bomarsund fortress complex in the Åland Islands.
  • 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. Aalborg Tower
    Aalborg Tower is a prominent observation tower in Aalborg, Denmark, known for its panoramic city views and distinctive steel structure.
  • E. Mjøstårnet
    Mjøstårnet is a pioneering high-rise timber building in Norway recognized as one of the tallest wooden structures in the 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6257937d081909dbc5804d2505938 completed April 20, 2026, 1:09 p.m.
Created at: April 10, 2026, 1:36 p.m.