Triple

T19785076
Position Surface form Disambiguated ID Type / Status
Subject Bornsjön E475240 entity
Predicate hasOutflow P967 FINISHED
Object Tumbaån
Tumbaån is a small river in Sweden that drains the lake Bornsjön and flows through the southern Stockholm region.
 E1396385 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: Tumbaån | Statement: [Bornsjön, hasOutflow, Tumbaån]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tumbaån
Context triple: [Bornsjön, hasOutflow, Tumbaån]
  • A. Hamngatan
    Hamngatan is a major shopping and traffic street in central Stockholm, Sweden, known for its department stores and proximity to Sergels torg.
  • B. Värtavägen
    Värtavägen is a street in Stockholm, Sweden, located in the Östermalm area and connecting the city center with the Värtahamnen harbor district.
  • C. Korsvägen
    Korsvägen is a major public square and transport hub in central Gothenburg, Sweden, known for its proximity to several of the city’s key event and cultural venues.
  • D. Hagestein
    Hagestein is a small village in the Dutch province of Utrecht, known for its historic church and rural character along the Lek River.
  • E. Tungelsta
    Tungelsta is a locality in Stockholm County, Sweden, known for its residential character and commuter connections within the Haninge area.
  • 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: Tumbaån
Triple: [Bornsjön, hasOutflow, Tumbaån]
Generated description
Tumbaån is a small river in Sweden that drains the lake Bornsjön and flows through the southern Stockholm region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tumbaån
Target entity description: Tumbaån is a small river in Sweden that drains the lake Bornsjön and flows through the southern Stockholm region.
  • A. Hamngatan
    Hamngatan is a major shopping and traffic street in central Stockholm, Sweden, known for its department stores and proximity to Sergels torg.
  • B. Värtavägen
    Värtavägen is a street in Stockholm, Sweden, located in the Östermalm area and connecting the city center with the Värtahamnen harbor district.
  • C. Korsvägen
    Korsvägen is a major public square and transport hub in central Gothenburg, Sweden, known for its proximity to several of the city’s key event and cultural venues.
  • D. Hagestein
    Hagestein is a small village in the Dutch province of Utrecht, known for its historic church and rural character along the Lek River.
  • E. Tungelsta
    Tungelsta is a locality in Stockholm County, Sweden, known for its residential character and commuter connections within the Haninge area.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6538715b8819080c6930e7d16ab58 completed April 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07c4f9ce188190b13dc532b5168af0 completed May 16, 2026, 1:14 a.m.
NEDg Description generation batch_6a07c944eda8819090d9355cf586fd90 completed May 16, 2026, 1:32 a.m.
NED2 Entity disambiguation (via description) batch_6a07ca06a7d48190aabeefe320e339e1 completed May 16, 2026, 1:36 a.m.
Created at: April 10, 2026, 1:49 p.m.