Triple

T8445318
Position Surface form Disambiguated ID Type / Status
Subject Storsjön E199658 entity
Predicate hasIsland P970 FINISHED
Object Andersön
Andersön is a large forested island in Sweden’s Lake Storsjön, known for its nature reserve, hiking trails, and rich birdlife.
E734639 NE FINISHED

How this triple was built (4 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: Andersön | Statement: [Storsjön, hasIsland, Andersön]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andersön
Context triple: [Storsjön, hasIsland, Andersön]
  • A. Söderfors
    Söderfors is a small locality in Uppsala County, Sweden, known historically for its ironworks and scenic location by the Dalälven river.
  • B. Leijonborg
    Leijonborg is a Swedish surname most notably associated with politician Lars Leijonborg, a former leader of the Liberal People's Party in Sweden.
  • C. Olofström
    Olofström is a small industrial town in southern Sweden known for its automotive manufacturing, particularly its long association with Volvo.
  • D. Wästberg
    Wästberg is a Swedish surname associated with notable figures in politics, literature, and public life.
  • E. Pedersöre
    Pedersöre is a bilingual (Swedish- and Finnish-speaking) rural municipality in western Finland known for its agriculture and small-town communities.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Andersön
Triple: [Storsjön, hasIsland, Andersön]
Generated description
Andersön is a large forested island in Sweden’s Lake Storsjön, known for its nature reserve, hiking trails, and rich birdlife.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andersön
Target entity description: Andersön is a large forested island in Sweden’s Lake Storsjön, known for its nature reserve, hiking trails, and rich birdlife.
  • A. Söderfors
    Söderfors is a small locality in Uppsala County, Sweden, known historically for its ironworks and scenic location by the Dalälven river.
  • B. Leijonborg
    Leijonborg is a Swedish surname most notably associated with politician Lars Leijonborg, a former leader of the Liberal People's Party in Sweden.
  • C. Olofström
    Olofström is a small industrial town in southern Sweden known for its automotive manufacturing, particularly its long association with Volvo.
  • D. Wästberg
    Wästberg is a Swedish surname associated with notable figures in politics, literature, and public life.
  • E. Pedersöre
    Pedersöre is a bilingual (Swedish- and Finnish-speaking) rural municipality in western Finland known for its agriculture and small-town communities.
  • F. None of above. chosen

Provenance (5 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_69ca83170f9081909cd98f55614c6476 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe3138ee08190918cd82adbe2d9a1 completed March 31, 2026, 3:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1dac8cb08190b74985a6ba3c938f completed April 2, 2026, 7:41 a.m.
NEDg Description generation batch_69ce1f3729e4819084600862b53c94a8 completed April 2, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_69ce1fdde53c8190b356950f878b6b70 completed April 2, 2026, 7:50 a.m.
Created at: March 30, 2026, 6:09 p.m.