Triple

T15021209
Position Surface form Disambiguated ID Type / Status
Subject Norwegian State Railways E378087 entity
Predicate successor P78 FINISHED
Object Rom Eiendom
Rom Eiendom is a Norwegian real estate company that manages and develops properties associated with the country’s railway infrastructure.
E1134067 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: Rom Eiendom | Statement: [Norwegian State Railways, successor, Rom Eiendom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rom Eiendom
Context triple: [Norwegian State Railways, successor, Rom Eiendom]
  • A. Boende
    Boende is a town in the Democratic Republic of the Congo that serves as an important local center of trade and administration in the Tshuapa Province.
  • B. Rohdenhaus
    Rohdenhaus is a district or locality within the town of Wülfrath in North Rhine-Westphalia, Germany.
  • C. Bygdøy Royal Estate
    Bygdøy Royal Estate is a historic royal property on the Bygdøy peninsula in Oslo that serves as one of the official residences of Norway’s monarch.
  • D. Royal Sommerhus
    Royal Sommerhus is a Frozen-themed meet-and-greet location at Epcot’s Norway Pavilion where guests can visit Anna and Elsa in their summer cabin.
  • E. Eilert Sundts hus
    Eilert Sundts hus is a main academic building at the University of Oslo that houses key social science departments, including the Institute of Economics.
  • 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: Rom Eiendom
Triple: [Norwegian State Railways, successor, Rom Eiendom]
Generated description
Rom Eiendom is a Norwegian real estate company that manages and develops properties associated with the country’s railway infrastructure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rom Eiendom
Target entity description: Rom Eiendom is a Norwegian real estate company that manages and develops properties associated with the country’s railway infrastructure.
  • A. Boende
    Boende is a town in the Democratic Republic of the Congo that serves as an important local center of trade and administration in the Tshuapa Province.
  • B. Rohdenhaus
    Rohdenhaus is a district or locality within the town of Wülfrath in North Rhine-Westphalia, Germany.
  • C. Bygdøy Royal Estate
    Bygdøy Royal Estate is a historic royal property on the Bygdøy peninsula in Oslo that serves as one of the official residences of Norway’s monarch.
  • D. Royal Sommerhus
    Royal Sommerhus is a Frozen-themed meet-and-greet location at Epcot’s Norway Pavilion where guests can visit Anna and Elsa in their summer cabin.
  • E. Eilert Sundts hus
    Eilert Sundts hus is a main academic building at the University of Oslo that houses key social science departments, including the Institute of Economics.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded765462c819097f331c9b39c80e3 completed April 15, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd2c96c8190a0368678584aaa16 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fea0c35b088190abf578ed016753cd completed May 9, 2026, 2:49 a.m.
NED2 Entity disambiguation (via description) batch_69fea16b16b8819080b31203189f8cfe completed May 9, 2026, 2:52 a.m.
Created at: April 10, 2026, 2:56 a.m.