Triple

T8508883
Position Surface form Disambiguated ID Type / Status
Subject Alexandra Exter E201403 entity
Predicate familyName P18 FINISHED
Object Ekster
Ekster is the surname of Alexandra Exter, a prominent Russian-Ukrainian avant-garde painter and stage designer associated with Cubism and Futurism.
E738390 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: Ekster | Statement: [Alexandra Exter, familyName, Ekster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ekster
Context triple: [Alexandra Exter, familyName, Ekster]
  • A. Sylko
    Sylko is a brand of sewing and embroidery threads historically associated with the textile company J. & P. Coats.
  • B. Rockwilder
    Rockwilder is an American hip-hop and R&B record producer known for his hard-hitting, polished sound and collaborations with major artists across the late 1990s and 2000s.
  • C. Modrow
    Modrow is a German surname most notably associated with Hans Modrow, the last communist premier of East Germany.
  • D. Blix
    Blix is a Swedish surname most notably associated with Hans Blix, the former head of the International Atomic Energy Agency and UN weapons inspector.
  • E. Blix
    Blix is a 19th-century novel by American naturalist writer Frank Norris that follows a young woman’s coming-of-age and romantic experiences in San Francisco.
  • 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: Ekster
Triple: [Alexandra Exter, familyName, Ekster]
Generated description
Ekster is the surname of Alexandra Exter, a prominent Russian-Ukrainian avant-garde painter and stage designer associated with Cubism and Futurism.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ekster
Target entity description: Ekster is the surname of Alexandra Exter, a prominent Russian-Ukrainian avant-garde painter and stage designer associated with Cubism and Futurism.
  • A. Sylko
    Sylko is a brand of sewing and embroidery threads historically associated with the textile company J. & P. Coats.
  • B. Rockwilder
    Rockwilder is an American hip-hop and R&B record producer known for his hard-hitting, polished sound and collaborations with major artists across the late 1990s and 2000s.
  • C. Modrow
    Modrow is a German surname most notably associated with Hans Modrow, the last communist premier of East Germany.
  • D. Blix
    Blix is a Swedish surname most notably associated with Hans Blix, the former head of the International Atomic Energy Agency and UN weapons inspector.
  • E. Blix
    Blix is a 19th-century novel by American naturalist writer Frank Norris that follows a young woman’s coming-of-age and romantic experiences in San Francisco.
  • 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_69ca8320e5748190ac2c585a0bba8193 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5df74e8819086b1445cc907e371 completed March 31, 2026, 3:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4e3faa0c81908533e9097ed29b26 completed April 2, 2026, 11:08 a.m.
NEDg Description generation batch_69ce4ff9792c81908d76141904a170bc completed April 2, 2026, 11:16 a.m.
NED2 Entity disambiguation (via description) batch_69ce50acae5881908f1d2c0e21dd7f1d completed April 2, 2026, 11:19 a.m.
Created at: March 30, 2026, 6:15 p.m.