Triple

T17468241
Position Surface form Disambiguated ID Type / Status
Subject Campus Fryslân E425332 entity
Predicate shortName P43 FINISHED
Object CF
CF is the abbreviation for Campus Fryslân, a faculty of the University of Groningen in the Netherlands focused on interdisciplinary and regional studies.
 E1271303 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: CF | Statement: [Campus Fryslân, shortName, CF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CF
Context triple: [Campus Fryslân, shortName, CF]
  • A. CF
    CF is the two-letter ISO 3166-1 alpha-2 country code assigned to the Central African Republic.
  • B. CF
    CF is a UK postcode area covering Cardiff and surrounding parts of South Wales, including the Vale of Glamorgan.
  • C. CF
    CF is the commonly used abbreviation for the Swiss Federal Council, the collective head of state and government of Switzerland.
  • D. CF
    CF is the abbreviation for the Commonwealth Foundation, an intergovernmental organization that supports civil society and promotes democracy and development across the Commonwealth.
  • E. FC
    FC is the chassis code for the second-generation Mazda RX-7 sports car produced in the late 1980s and early 1990s.
  • 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: CF
Triple: [Campus Fryslân, shortName, CF]
Generated description
CF is the abbreviation for Campus Fryslân, a faculty of the University of Groningen in the Netherlands focused on interdisciplinary and regional studies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CF
Target entity description: CF is the abbreviation for Campus Fryslân, a faculty of the University of Groningen in the Netherlands focused on interdisciplinary and regional studies.
  • A. CF
    CF is the abbreviation for the Commonwealth Foundation, an intergovernmental organization that supports civil society and promotes democracy and development across the Commonwealth.
  • B. CF
    CF is a UK postcode area covering Cardiff and surrounding parts of South Wales, including the Vale of Glamorgan.
  • C. CF
    CF is the two-letter ISO 3166-1 alpha-2 country code assigned to the Central African Republic.
  • D. CF
    CF is the commonly used abbreviation for the Swiss Federal Council, the collective head of state and government of Switzerland.
  • E. FC
    FC is the chassis code for the second-generation Mazda RX-7 sports car produced in the late 1980s and early 1990s.
  • 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_69d889dbc2e88190b18ea6115e819258 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451aa0e1c81909627369465575c06 completed April 19, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01b827bad4819083e1814183fe24a1 completed May 11, 2026, 11:06 a.m.
NEDg Description generation batch_6a01bca7ce18819085b00fe298b89492 completed May 11, 2026, 11:25 a.m.
NED2 Entity disambiguation (via description) batch_6a01bd3d64048190bb7e3acf2b460128 completed May 11, 2026, 11:27 a.m.
Created at: April 10, 2026, 5:47 a.m.