Triple

T2587931
Position Surface form Disambiguated ID Type / Status
Subject Carlson E58048 entity
Predicate relatedSurname P13741 FINISHED
Object Karlssen
Karlssen is a Scandinavian-origin surname, likely a patronymic variant related to the more common name Carlson.
E278828 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: Karlssen | Statement: [Carlson, relatedSurname, Karlssen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karlssen
Context triple: [Carlson, relatedSurname, Karlssen]
  • A. Nilsen
    Nilsen is a surname, primarily of Scandinavian origin, that serves as a variant spelling of Nelson.
  • B. Ole Einar
    Ole Einar is a Norwegian former biathlete widely regarded as one of the greatest in the sport’s history.
  • C. Bjørn Kjos
    Bjørn Kjos is a Norwegian businessman, lawyer, and former fighter pilot best known as the co-founder and long-time CEO of the low-cost airline Norwegian Air Shuttle.
  • D. Morten
    Morten is a masculine given name commonly used in Scandinavian countries, derived from the Latin name Martinus.
  • E. Knut Pedersen
    Knut Pedersen, better known by his pen name Knut Hamsun, was a Norwegian novelist and Nobel Prize laureate renowned for his influential modernist works such as "Hunger" and "Growth of the Soil."
  • 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: Karlssen
Triple: [Carlson, relatedSurname, Karlssen]
Generated description
Karlssen is a Scandinavian-origin surname, likely a patronymic variant related to the more common name Carlson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karlssen
Target entity description: Karlssen is a Scandinavian-origin surname, likely a patronymic variant related to the more common name Carlson.
  • A. Nilsen
    Nilsen is a surname, primarily of Scandinavian origin, that serves as a variant spelling of Nelson.
  • B. Ole Einar
    Ole Einar is a Norwegian former biathlete widely regarded as one of the greatest in the sport’s history.
  • C. Bjørn Kjos
    Bjørn Kjos is a Norwegian businessman, lawyer, and former fighter pilot best known as the co-founder and long-time CEO of the low-cost airline Norwegian Air Shuttle.
  • D. Morten
    Morten is a masculine given name commonly used in Scandinavian countries, derived from the Latin name Martinus.
  • E. Knut Pedersen
    Knut Pedersen, better known by his pen name Knut Hamsun, was a Norwegian novelist and Nobel Prize laureate renowned for his influential modernist works such as "Hunger" and "Growth of the Soil."
  • 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_69ab4ac019c8819094add11c46706e32 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd3f8a3888190889c537e6df07305 completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69af65848e788190b2b01595540b1a10 completed March 10, 2026, 12:27 a.m.
NEDg Description generation batch_69af6694dd248190ad6d579d504b5f27 completed March 10, 2026, 12:32 a.m.
NED2 Entity disambiguation (via description) batch_69af677577c88190be9a66fea85ab899 completed March 10, 2026, 12:36 a.m.
Created at: March 6, 2026, 9:49 p.m.