Triple

T1837267
Position Surface form Disambiguated ID Type / Status
Subject Swedish Army E41092 entity
Predicate garrison P75 FINISHED
Object Skövde
Skövde is a town in south-central Sweden that serves as a major military hub and training center for the Swedish Army.
 E275769 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: Skövde | Statement: [Swedish Army, garrison, Skövde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Skövde
Context triple: [Swedish Army, garrison, Skövde]
  • A. Sundsvall
    Sundsvall is a coastal city in central Sweden known as an important industrial and commercial center on the Gulf of Bothnia.
  • B. Nyköping
    Nyköping is a historic coastal town in southeastern Sweden known for its medieval castle, harbor, and role as a regional administrative and cultural center.
  • C. Jönköping
    Jönköping is a city in southern Sweden, located at the southern end of Lake Vättern and known as a regional commercial and logistical hub.
  • D. Trollhättan
    Trollhättan is a city in western Sweden known for its historic role in the automotive industry and as the longtime home of Saab Automobile’s main production facilities.
  • E. Eskilstuna
    Eskilstuna is an industrial city in central Sweden known historically for its metalworking and engineering industries.
  • 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: Skövde
Triple: [Swedish Army, garrison, Skövde]
Generated description
Skövde is a town in south-central Sweden that serves as a major military hub and training center for the Swedish Army.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Skövde
Target entity description: Skövde is a town in south-central Sweden that serves as a major military hub and training center for the Swedish Army.
  • A. Sundsvall
    Sundsvall is a coastal city in central Sweden known as an important industrial and commercial center on the Gulf of Bothnia.
  • B. Nyköping
    Nyköping is a historic coastal town in southeastern Sweden known for its medieval castle, harbor, and role as a regional administrative and cultural center.
  • C. Jönköping
    Jönköping is a city in southern Sweden, located at the southern end of Lake Vättern and known as a regional commercial and logistical hub.
  • D. Trollhättan
    Trollhättan is a city in western Sweden known for its historic role in the automotive industry and as the longtime home of Saab Automobile’s main production facilities.
  • E. Eskilstuna
    Eskilstuna is an industrial city in central Sweden known historically for its metalworking and engineering industries.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0380a4c81909a2ad0bfd97c884a completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b4b974081908da05bc63f923215 completed March 9, 2026, 8:19 p.m.
NEDg Description generation batch_69af508c28f48190afc4aa1bc3c9adf3 completed March 9, 2026, 10:58 p.m.
NED2 Entity disambiguation (via description) batch_69af5155f85081908dd4a1859d0f7907 completed March 9, 2026, 11:01 p.m.
Created at: March 4, 2026, 7:33 p.m.