Triple

T15030186
Position Surface form Disambiguated ID Type / Status
Subject T-bana E378321 entity
Predicate hasStation P35 FINISHED
Object Fruängen
Fruängen is a Stockholm metro station on the red line, serving as the terminus of one of its southern branches in the Fruängen district.
 E1134018 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: Fruängen | Statement: [T-bana, hasStation, Fruängen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fruängen
Context triple: [T-bana, hasStation, Fruängen]
  • A. Lány
    Lány is a village and chateau area in the Czech Republic known as the site of the presidential summer residence and the place where the first Czechoslovak president Tomáš Garrigue Masaryk died.
  • B. Lillafüred
    Lillafüred is a scenic resort area in northern Hungary known for its historic palace hotel, hanging gardens, and proximity to natural attractions like caves and waterfalls.
  • C. Tjejvasan
    Tjejvasan is a popular women-only cross-country ski race in Sweden that forms part of the larger Vasaloppet series.
  • D. Majgull
    Majgull is a Swedish given name, notably borne by the acclaimed author Majgull Axelsson.
  • E. Jungfrun
    Jungfrun is a small, uninhabited island in Sweden’s Lake Vättern, known for its steep cliffs and protected natural environment.
  • 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: Fruängen
Triple: [T-bana, hasStation, Fruängen]
Generated description
Fruängen is a Stockholm metro station on the red line, serving as the terminus of one of its southern branches in the Fruängen district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fruängen
Target entity description: Fruängen is a Stockholm metro station on the red line, serving as the terminus of one of its southern branches in the Fruängen district.
  • A. Lány
    Lány is a village and chateau area in the Czech Republic known as the site of the presidential summer residence and the place where the first Czechoslovak president Tomáš Garrigue Masaryk died.
  • B. Lillafüred
    Lillafüred is a scenic resort area in northern Hungary known for its historic palace hotel, hanging gardens, and proximity to natural attractions like caves and waterfalls.
  • C. Tjejvasan
    Tjejvasan is a popular women-only cross-country ski race in Sweden that forms part of the larger Vasaloppet series.
  • D. Majgull
    Majgull is a Swedish given name, notably borne by the acclaimed author Majgull Axelsson.
  • E. Jungfrun
    Jungfrun is a small, uninhabited island in Sweden’s Lake Vättern, known for its steep cliffs and protected natural environment.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e2416081908dfba48d7f7b4a84 completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd967588190821cf47e9734db21 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9e5dbbe0819084567688758b0245 completed May 9, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_69fe9eedca1481908ce438991184d62e completed May 9, 2026, 2:41 a.m.
Created at: April 10, 2026, 2:59 a.m.