Triple

T16997394
Position Surface form Disambiguated ID Type / Status
Subject Ehrnrooth E412352 entity
Predicate hasNotableMember P304 FINISHED
Object Henrik Ehrnrooth
Henrik Ehrnrooth is a Finnish business executive best known as the president and CEO of KONE Corporation, a global leader in the elevator and escalator industry.
E1250380 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: Henrik Ehrnrooth | Statement: [Ehrnrooth, hasNotableMember, Henrik Ehrnrooth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henrik Ehrnrooth
Context triple: [Ehrnrooth, hasNotableMember, Henrik Ehrnrooth]
  • A. Georg Ehrnrooth
    Georg Ehrnrooth was a prominent Finnish politician and lawyer known for his conservative views and long tenure as a member of the Finnish Parliament.
  • B. Bertil Huttunen
    Bertil Huttunen was an architect associated with the design of Toronto City Hall.
  • C. Eero Jukola
    Eero Jukola is one of the seven Jukola brothers in Aleksis Kivi’s classic Finnish novel "Seven Brothers," known for his intelligence and reflective nature.
  • D. Vilho Hirvensalo
    Vilho Hirvensalo is a Finnish mathematician known for his work in computational complexity theory and quantum computing.
  • E. Eero Heinonen
    Eero Heinonen is a Finnish musician best known as the longtime bassist of the rock band The Rasmus.
  • 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: Henrik Ehrnrooth
Triple: [Ehrnrooth, hasNotableMember, Henrik Ehrnrooth]
Generated description
Henrik Ehrnrooth is a Finnish business executive best known as the president and CEO of KONE Corporation, a global leader in the elevator and escalator industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Henrik Ehrnrooth
Target entity description: Henrik Ehrnrooth is a Finnish business executive best known as the president and CEO of KONE Corporation, a global leader in the elevator and escalator industry.
  • A. Georg Ehrnrooth
    Georg Ehrnrooth was a prominent Finnish politician and lawyer known for his conservative views and long tenure as a member of the Finnish Parliament.
  • B. Bertil Huttunen
    Bertil Huttunen was an architect associated with the design of Toronto City Hall.
  • C. Eero Jukola
    Eero Jukola is one of the seven Jukola brothers in Aleksis Kivi’s classic Finnish novel "Seven Brothers," known for his intelligence and reflective nature.
  • D. Vilho Hirvensalo
    Vilho Hirvensalo is a Finnish mathematician known for his work in computational complexity theory and quantum computing.
  • E. Eero Heinonen
    Eero Heinonen is a Finnish musician best known as the longtime bassist of the rock band The Rasmus.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d2885f888190ab1406f55a91bf93 completed April 18, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0139ed3c5c8190b9d3662378ead04c completed May 11, 2026, 2:07 a.m.
NEDg Description generation batch_6a013ae388548190b09d2c81e1ab0d02 completed May 11, 2026, 2:11 a.m.
NED2 Entity disambiguation (via description) batch_6a013b4df74c81908b3b99e276531e13 completed May 11, 2026, 2:13 a.m.
Created at: April 10, 2026, 5:32 a.m.