Triple

T17022320
Position Surface form Disambiguated ID Type / Status
Subject Lejonbacken E412975 entity
Predicate hasView P854 FINISHED
Object Helgeandsholmen E297374 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: Helgeandsholmen | Statement: [Lejonbacken, hasView, Helgeandsholmen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helgeandsholmen
Context triple: [Lejonbacken, hasView, Helgeandsholmen]
  • A. Helgeandsholmen chosen
    Helgeandsholmen is a small central Stockholm islet best known as the site of the Swedish Parliament building and part of the historic city core.
  • B. Blasieholmen
    Blasieholmen is a central Stockholm peninsula known for its historic buildings, cultural institutions, and waterfront views across from the Old Town.
  • C. Røsholmholmen
    Røsholmholmen is a small island located in Tyrifjorden, a large lake in southeastern Norway.
  • D. Heggholmen
    Heggholmen is a small island in the Oslofjord near Oslo, Norway, known for its coastal scenery and proximity to other islets like Gressholmen.
  • E. Stadsholmen
    Stadsholmen is the central island in Stockholm’s historic Gamla stan (Old Town), known for its medieval street layout and well-preserved architecture.
  • 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.