Triple

T21320716
Position Surface form Disambiguated ID Type / Status
Subject Sveavägen E525605 entity
Predicate runsTo P2127 FINISHED
Object Haga Södra 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: Haga Södra | Statement: [Sveavägen, runsTo, Haga Södra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haga Södra
Context triple: [Sveavägen, runsTo, Haga Södra]
  • A. Haga Södra chosen
    Haga Södra is a southern district of the Haga area in Stockholm, Sweden, known for its proximity to central city streets and parklands.
  • B. Hägersten
    Hägersten is a residential district in southern Stockholm, Sweden, known for its mix of apartment blocks, green areas, and proximity to the city center.
  • C. Sollerön
    Sollerön is the largest island in Lake Siljan in central Sweden, known for its traditional Dalarna culture and scenic rural landscapes.
  • D. Seskarö
    Seskarö is a Swedish island in the northern Baltic Sea known for its forests, beaches, and traditional fishing and forestry communities.
  • E. Kungsbacka
    Kungsbacka is a town in southwestern Sweden known for its coastal location, historic wooden center, and role as a commuter hub for nearby Gothenburg.
  • 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_69e0b51ad810819098c12392c8e55f6c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e77ed0a2788190b6a71c8c720173dc completed April 21, 2026, 1:42 p.m.
Created at: April 16, 2026, 4:39 p.m.