Triple

T5966152
Position Surface form Disambiguated ID Type / Status
Subject Dan Flavin E132756 entity
Predicate spouse P13 FINISHED
Object Sonja Severdija
Sonja Severdija is best known as the wife of minimalist light artist Dan Flavin.
E560918 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: Sonja Severdija | Statement: [Dan Flavin, spouse, Sonja Severdija]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonja Severdija
Context triple: [Dan Flavin, spouse, Sonja Severdija]
  • A. Sanda Dubravčić
    Sanda Dubravčić is a former Yugoslav figure skater best known for lighting the Olympic cauldron at the 1984 Winter Olympics in Sarajevo.
  • B. Nena Danevic
    Nena Danevic is a film editor best known for her Academy Award–winning work on the 1984 historical drama "Amadeus."
  • C. Nataša Kandić
    Nataša Kandić is a Serbian human rights activist known for documenting war crimes and advocating for justice and reconciliation in the former Yugoslavia.
  • D. Célia Šašić
    Célia Šašić is a retired German footballer and prolific striker who was one of Europe’s top scorers and a key figure for both the German national team and 1. FFC Frankfurt.
  • E. Milena Vukotić
    Milena Vukotić was the Queen consort of Montenegro and a prominent 19th–20th century Balkan royal figure known for her political influence and role in modernizing the Montenegrin court.
  • 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: Sonja Severdija
Triple: [Dan Flavin, spouse, Sonja Severdija]
Generated description
Sonja Severdija is best known as the wife of minimalist light artist Dan Flavin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sonja Severdija
Target entity description: Sonja Severdija is best known as the wife of minimalist light artist Dan Flavin.
  • A. Sanda Dubravčić
    Sanda Dubravčić is a former Yugoslav figure skater best known for lighting the Olympic cauldron at the 1984 Winter Olympics in Sarajevo.
  • B. Nena Danevic
    Nena Danevic is a film editor best known for her Academy Award–winning work on the 1984 historical drama "Amadeus."
  • C. Nataša Kandić
    Nataša Kandić is a Serbian human rights activist known for documenting war crimes and advocating for justice and reconciliation in the former Yugoslavia.
  • D. Célia Šašić
    Célia Šašić is a retired German footballer and prolific striker who was one of Europe’s top scorers and a key figure for both the German national team and 1. FFC Frankfurt.
  • E. Milena Vukotić
    Milena Vukotić was the Queen consort of Montenegro and a prominent 19th–20th century Balkan royal figure known for her political influence and role in modernizing the Montenegrin court.
  • 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_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a3e06848190b1d1a191db257a07 completed March 22, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1083b22788190be47b593b30184c6 completed March 23, 2026, 9:30 a.m.
NEDg Description generation batch_69c1095d98c08190b43e84642af701f0 completed March 23, 2026, 9:35 a.m.
NED2 Entity disambiguation (via description) batch_69c10a5e061c81909e8085f3210452dc completed March 23, 2026, 9:39 a.m.
Created at: March 22, 2026, 4:03 p.m.