Triple

T8399858
Position Surface form Disambiguated ID Type / Status
Subject Theo van Doesburg E198144 entity
Predicate pseudonym P39 FINISHED
Object I. K. Bonset
I. K. Bonset was a literary pseudonym used by Dutch artist and De Stijl co-founder Theo van Doesburg for his experimental and Dada-influenced writings.
 E730665 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: I. K. Bonset | Statement: [Theo van Doesburg, pseudonym, I. K. Bonset]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: I. K. Bonset
Context triple: [Theo van Doesburg, pseudonym, I. K. Bonset]
  • A. Herman Saftleven
    Herman Saftleven was a 17th-century Dutch painter and draughtsman known for his detailed river landscapes and topographical views.
  • B. I.M. Skaugen
    I.M. Skaugen was a Norwegian shipping magnate and entrepreneur known for his influential role in the global cruise and maritime industries.
  • C. Ernst Peterson
    Ernst Peterson was a German military officer who commanded the Zeppelin airship LZ 37 during World War I.
  • D. Paul Boray
    Paul Boray is the driven, emotionally tormented violinist protagonist of the film "Humoresque," whose passion for music shapes his turbulent personal and professional life.
  • E. Karl Kebach
    Karl Kebach was a landscape architect known for designing the park surrounding the Vorontsov Palace in Crimea.
  • 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: I. K. Bonset
Triple: [Theo van Doesburg, pseudonym, I. K. Bonset]
Generated description
I. K. Bonset was a literary pseudonym used by Dutch artist and De Stijl co-founder Theo van Doesburg for his experimental and Dada-influenced writings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: I. K. Bonset
Target entity description: I. K. Bonset was a literary pseudonym used by Dutch artist and De Stijl co-founder Theo van Doesburg for his experimental and Dada-influenced writings.
  • A. Herman Saftleven
    Herman Saftleven was a 17th-century Dutch painter and draughtsman known for his detailed river landscapes and topographical views.
  • B. I.M. Skaugen
    I.M. Skaugen was a Norwegian shipping magnate and entrepreneur known for his influential role in the global cruise and maritime industries.
  • C. Ernst Peterson
    Ernst Peterson was a German military officer who commanded the Zeppelin airship LZ 37 during World War I.
  • D. Paul Boray
    Paul Boray is the driven, emotionally tormented violinist protagonist of the film "Humoresque," whose passion for music shapes his turbulent personal and professional life.
  • E. Karl Kebach
    Karl Kebach was a landscape architect known for designing the park surrounding the Vorontsov Palace in Crimea.
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb824bfcbc8190b26bfcb5f8c4777c completed March 31, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde86f6e148190812a8a9737310501 completed April 2, 2026, 3:54 a.m.
NEDg Description generation batch_69cdebfd60188190a1681344e2bf1e9e completed April 2, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_69cded2fa42c8190bfbfc79caf38bf8e completed April 2, 2026, 4:14 a.m.
Created at: March 30, 2026, 6:04 p.m.