Triple

T7770499
Position Surface form Disambiguated ID Type / Status
Subject Ångerman River E179055 entity
Predicate flowsThrough P225 FINISHED
Object Sollefteå
Sollefteå is a small town in northern Sweden known for its scenic location along the Ångerman River and its surrounding forests and hills.
 E691531 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: Sollefteå | Statement: [Ångerman River, flowsThrough, Sollefteå]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sollefteå
Context triple: [Ångerman River, flowsThrough, Sollefteå]
  • A. Farsund
    Farsund is a coastal town and municipality in southern Norway known for its maritime heritage, beaches, and historic wooden architecture.
  • B. Sölvesborg
    Sölvesborg is a coastal town in southern Sweden known for its medieval architecture, historic town center, and location on the Baltic Sea in Blekinge County.
  • C. Trosa
    Trosa is a small coastal town in Södermanland County, Sweden, known for its picturesque wooden houses, harbor, and tourism.
  • D. Bojnord
    Bojnord is a city in northeastern Iran that serves as the capital of North Khorasan Province.
  • E. Sandvika
    Sandvika is a town in southeastern Norway that serves as the administrative center of Bærum and a commercial hub in the Greater Oslo Region.
  • 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: Sollefteå
Triple: [Ångerman River, flowsThrough, Sollefteå]
Generated description
Sollefteå is a small town in northern Sweden known for its scenic location along the Ångerman River and its surrounding forests and hills.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sollefteå
Target entity description: Sollefteå is a small town in northern Sweden known for its scenic location along the Ångerman River and its surrounding forests and hills.
  • A. Farsund
    Farsund is a coastal town and municipality in southern Norway known for its maritime heritage, beaches, and historic wooden architecture.
  • B. Sölvesborg
    Sölvesborg is a coastal town in southern Sweden known for its medieval architecture, historic town center, and location on the Baltic Sea in Blekinge County.
  • C. Trosa
    Trosa is a small coastal town in Södermanland County, Sweden, known for its picturesque wooden houses, harbor, and tourism.
  • D. Bojnord
    Bojnord is a city in northeastern Iran that serves as the capital of North Khorasan Province.
  • E. Sandvika
    Sandvika is a town in southeastern Norway that serves as the administrative center of Bærum and a commercial hub in the Greater Oslo Region.
  • 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_69c69f30602c819082ab52cd4af5c592 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c70438ca2481909114b0c434717109 completed March 27, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c98bdf24bc81909b8d3f519d48ce98 completed March 29, 2026, 8:30 p.m.
NEDg Description generation batch_69c98d016f6c8190b00c231959a967da completed March 29, 2026, 8:35 p.m.
NED2 Entity disambiguation (via description) batch_69c98d567efc819096aeecc5c6e986f8 completed March 29, 2026, 8:36 p.m.
Created at: March 27, 2026, 4:11 p.m.