Triple

T14393586
Position Surface form Disambiguated ID Type / Status
Subject Heikki Mannila E356902 entity
Predicate familyName P18 FINISHED
Object Mannila
Mannila is a Finnish surname borne by individuals such as computer scientist Heikki Mannila.
 E1108012 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: Mannila | Statement: [Heikki Mannila, familyName, Mannila]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mannila
Context triple: [Heikki Mannila, familyName, Mannila]
  • A. Helsinki
    Helsinki is the capital and largest city of Finland, known for its coastal location on the Baltic Sea, modern design, and vibrant cultural life.
  • B. Espoo
    Espoo is Finland’s second-largest city, located just west of Helsinki on the southern coast, known for its technology industry, natural landscapes, and role as part of the Helsinki metropolitan area.
  • C. Turku
    Turku is one of Finland’s oldest and historically most important cities, located on the southwest coast and known for its medieval heritage and major Baltic Sea port.
  • D. Tampere
    Tampere is a major industrial and cultural city in southern Finland, historically significant as a key battleground in the Finnish Civil War.
  • E. 42 Helsinki
    42 Helsinki is a Finnish campus of the global, tuition-free 42 coding school network, offering peer-to-peer, project-based software engineering education.
  • 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: Mannila
Triple: [Heikki Mannila, familyName, Mannila]
Generated description
Mannila is a Finnish surname borne by individuals such as computer scientist Heikki Mannila.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mannila
Target entity description: Mannila is a Finnish surname borne by individuals such as computer scientist Heikki Mannila.
  • A. Helsinki
    Helsinki is the capital and largest city of Finland, known for its coastal location on the Baltic Sea, modern design, and vibrant cultural life.
  • B. Espoo
    Espoo is Finland’s second-largest city, located just west of Helsinki on the southern coast, known for its technology industry, natural landscapes, and role as part of the Helsinki metropolitan area.
  • C. Turku
    Turku is one of Finland’s oldest and historically most important cities, located on the southwest coast and known for its medieval heritage and major Baltic Sea port.
  • D. Tampere
    Tampere is a major industrial and cultural city in southern Finland, historically significant as a key battleground in the Finnish Civil War.
  • E. 42 Helsinki
    42 Helsinki is a Finnish campus of the global, tuition-free 42 coding school network, offering peer-to-peer, project-based software engineering education.
  • 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de902d114881908a8f3c01b3c6d309 completed April 14, 2026, 7:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94a254f881908d9494d4602064ae completed May 8, 2026, 7:45 a.m.
NEDg Description generation batch_69fd96d7fd008190bd55c7ffbb8b6f1a completed May 8, 2026, 7:55 a.m.
NED2 Entity disambiguation (via description) batch_69fd971d73b08190b1896a1d9985b589 completed May 8, 2026, 7:56 a.m.
Created at: April 10, 2026, 1:16 a.m.