Triple

T17022309
Position Surface form Disambiguated ID Type / Status
Subject Lejonbacken E412975 entity
Predicate overlooks P1323 FINISHED
Object Norrström E78000 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: Norrström | Statement: [Lejonbacken, overlooks, Norrström]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norrström
Context triple: [Lejonbacken, overlooks, Norrström]
  • A. Norrström chosen
    Norrström is a short but significant river in central Stockholm that connects Lake Mälaren with the Baltic Sea and flows past several of the city’s key historic and governmental buildings.
  • B. Geijer
    Geijer is a Swedish surname most notably associated with Erik Gustaf Geijer, a prominent 19th-century writer, historian, and philosopher.
  • C. Norlén
    Norlén is a Swedish surname most notably borne by politician Andreas Norlén, the Speaker of the Riksdag.
  • D. Bäckström
    Bäckström is a Swedish surname most prominently associated with NHL ice hockey star Nicklas Bäckström.
  • E. Gyllensten
    Gyllensten is a Swedish surname most notably associated with Lars Gyllensten, a prominent author and former member of the Swedish Academy.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d1d2e48190bbcba129247c6c2e completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b4f9dfc819085639edb5cda1cca completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.