Triple

T1133933
Position Surface form Disambiguated ID Type / Status
Subject Åland Islands E23094 entity
Predicate capital P234 FINISHED
Object Mariehamn
Mariehamn is the main town and administrative, cultural, and economic center of the autonomous Åland Islands in the Baltic Sea.
 E137303 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: Mariehamn | Statement: [Åland Islands, capital, Mariehamn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mariehamn
Context triple: [Åland Islands, capital, Mariehamn]
  • A. Tromsø
    Tromsø is a city in northern Norway known for its Arctic location, vibrant cultural scene, and prominence as a viewing spot for the Northern Lights.
  • B. Ålesund
    Ålesund is a coastal Norwegian city renowned for its distinctive Art Nouveau architecture and location across several islands in Western Norway.
  • C. Bodø
    Bodø is a coastal city in northern Norway known as a regional hub for culture, transport, and access to Arctic nature.
  • D. Kristiansund
    Kristiansund is a coastal city in western Norway known for its historic clipfish industry, distinctive layout across several islands, and picturesque harbor.
  • E. Stavanger
    Stavanger is a coastal city in southwestern Norway known for its oil industry hub status, historic wooden houses, and proximity to natural attractions like the Lysefjord and Preikestolen.
  • 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: Mariehamn
Triple: [Åland Islands, capital, Mariehamn]
Generated description
Mariehamn is the main town and administrative, cultural, and economic center of the autonomous Åland Islands in the Baltic Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mariehamn
Target entity description: Mariehamn is the main town and administrative, cultural, and economic center of the autonomous Åland Islands in the Baltic Sea.
  • A. Tromsø
    Tromsø is a city in northern Norway known for its Arctic location, vibrant cultural scene, and prominence as a viewing spot for the Northern Lights.
  • B. Ålesund
    Ålesund is a coastal Norwegian city renowned for its distinctive Art Nouveau architecture and location across several islands in Western Norway.
  • C. Bodø
    Bodø is a coastal city in northern Norway known as a regional hub for culture, transport, and access to Arctic nature.
  • D. Kristiansund
    Kristiansund is a coastal city in western Norway known for its historic clipfish industry, distinctive layout across several islands, and picturesque harbor.
  • E. Stavanger
    Stavanger is a coastal city in southwestern Norway known for its oil industry hub status, historic wooden houses, and proximity to natural attractions like the Lysefjord and Preikestolen.
  • 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_69a493ec75988190b63a11bafaec29b4 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bbfe68008190b2307b8107f06a08 completed March 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac76405074819089f001916748b466 completed March 7, 2026, 7:02 p.m.
NEDg Description generation batch_69ac7864c59c8190bc2fa1ac8ce633db completed March 7, 2026, 7:11 p.m.
NED2 Entity disambiguation (via description) batch_69ac7c57dfe4819081903c188084993b completed March 7, 2026, 7:28 p.m.
Created at: March 1, 2026, 7:44 p.m.