Triple

T10467967
Position Surface form Disambiguated ID Type / Status
Subject Eurovision Song Contest 1991 E246849 entity
Predicate winningPerformer P46350 FINISHED
Object Carola
Carola is a Swedish pop singer best known for winning the Eurovision Song Contest in 1991 with the song "Fångad av en stormvind."
E865406 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: Carola | Statement: [Eurovision Song Contest 1991, winningPerformer, Carola]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carola
Context triple: [Eurovision Song Contest 1991, winningPerformer, Carola]
  • A. Carola
    Carola is a Dutch politician known for serving as Deputy Prime Minister and Minister of Agriculture, Nature and Food Quality in the Netherlands.
  • B. Lorena
    Lorena is a city in the state of São Paulo, Brazil, known for hosting a campus of the University of São Paulo.
  • C. Winona
    Winona is a historic river city in southeastern Minnesota known for its Mississippi River bluffs, cultural festivals, and regional educational institutions.
  • D. Tonina
    Tonina is an ancient Maya archaeological site in Chiapas, Mexico, known for its towering acropolis, intricate relief sculptures, and significant role in Classic-period Maya politics.
  • E. Carla
    Carla is a feminine given name commonly used in various languages, often considered the female form of Carl or Charles.
  • 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: Carola
Triple: [Eurovision Song Contest 1991, winningPerformer, Carola]
Generated description
Carola is a Swedish pop singer best known for winning the Eurovision Song Contest in 1991 with the song "Fångad av en stormvind."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carola
Target entity description: Carola is a Swedish pop singer best known for winning the Eurovision Song Contest in 1991 with the song "Fångad av en stormvind."
  • A. Carola
    Carola is a Dutch politician known for serving as Deputy Prime Minister and Minister of Agriculture, Nature and Food Quality in the Netherlands.
  • B. Lorena
    Lorena is a city in the state of São Paulo, Brazil, known for hosting a campus of the University of São Paulo.
  • C. Winona
    Winona is a historic river city in southeastern Minnesota known for its Mississippi River bluffs, cultural festivals, and regional educational institutions.
  • D. Tonina
    Tonina is an ancient Maya archaeological site in Chiapas, Mexico, known for its towering acropolis, intricate relief sculptures, and significant role in Classic-period Maya politics.
  • E. Carla
    Carla is a feminine given name commonly used in various languages, often considered the female form of Carl or Charles.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5092ef810819093a4d1df83aeac09 completed April 7, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89ff1cd948190a1ef331fb810bf26 completed April 10, 2026, 7 a.m.
NEDg Description generation batch_69d8a2b0d8c88190a1a64bd2bbacabbe completed April 10, 2026, 7:11 a.m.
NED2 Entity disambiguation (via description) batch_69d8a6560ddc81909d540f78a9413b3e completed April 10, 2026, 7:27 a.m.
Created at: April 6, 2026, 12:20 p.m.