Triple

T5431052
Position Surface form Disambiguated ID Type / Status
Subject Kungens kurva E121489 entity
Predicate adjacentTo P224 FINISHED
Object Segeltorp E121488 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: Segeltorp | Statement: [Kungens kurva, adjacentTo, Segeltorp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Segeltorp
Context triple: [Kungens kurva, adjacentTo, Segeltorp]
  • A. Segeltorp chosen
    Segeltorp is a suburban district in the southern part of the Stockholm urban area, located within Huddinge Municipality in Sweden.
  • B. Seiling
    Seiling is a small rural city in Dewey County, northwestern Oklahoma, known historically as a farming and ranching community.
  • C. Sollentuna
    Sollentuna is a suburban town in Stockholm County, Sweden, known as part of the Stockholm urban area and a residential and commercial hub just north of the capital.
  • D. Skibotn
    Skibotn is a small village in northern Norway known for its clear skies and role as a center for astronomical observations.
  • E. Holm
    Holm is a small rural settlement in the Orkney Islands of Scotland, known for its coastal landscape and historic island community.
  • 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_69bd463c65f0819082ee6483ab4b466a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd883e5e10819091e159dfd245e94d completed March 20, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3ac985e48190ba9610e0563c73ab completed March 22, 2026, 12:41 a.m.
Created at: March 20, 2026, 2:06 p.m.