Triple

T21356794
Position Surface form Disambiguated ID Type / Status
Subject Michael Brandt E526651 entity
Predicate spouse P13 FINISHED
Object Agata Brandt
Agata Brandt is the wife of Michael Brandt, known primarily in relation to him.
E1480533 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: Agata Brandt | Statement: [Michael Brandt, spouse, Agata Brandt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agata Brandt
Context triple: [Michael Brandt, spouse, Agata Brandt]
  • A. Kasia Ostlun
    Kasia Ostlun is the wife of American actor Jeffrey Tambor and the mother of several of his children.
  • B. Agata Kornhauser-Duda
    Agata Kornhauser-Duda is a Polish teacher and the First Lady of Poland, known for her role as the wife of President Andrzej Duda.
  • C. Natalia Czerwonka
    Natalia Czerwonka is a Polish speed skater and Olympic medalist who has represented Poland in multiple Winter Olympic Games.
  • D. Dagmara Handzlik
    Dagmara Handzlik is a Polish long-distance runner known for competing internationally in events such as the marathon and half marathon.
  • E. Monika Jaruzelska
    Monika Jaruzelska is a Polish journalist, writer, and former stylist, known both for her media work and as the daughter of Poland’s former communist leader Wojciech Jaruzelski.
  • 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: Agata Brandt
Triple: [Michael Brandt, spouse, Agata Brandt]
Generated description
Agata Brandt is the wife of Michael Brandt, known primarily in relation to him.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Agata Brandt
Target entity description: Agata Brandt is the wife of Michael Brandt, known primarily in relation to him.
  • A. Kasia Ostlun
    Kasia Ostlun is the wife of American actor Jeffrey Tambor and the mother of several of his children.
  • B. Agata Kornhauser-Duda
    Agata Kornhauser-Duda is a Polish teacher and the First Lady of Poland, known for her role as the wife of President Andrzej Duda.
  • C. Natalia Czerwonka
    Natalia Czerwonka is a Polish speed skater and Olympic medalist who has represented Poland in multiple Winter Olympic Games.
  • D. Dagmara Handzlik
    Dagmara Handzlik is a Polish long-distance runner known for competing internationally in events such as the marathon and half marathon.
  • E. Monika Jaruzelska
    Monika Jaruzelska is a Polish journalist, writer, and former stylist, known both for her media work and as the daughter of Poland’s former communist leader Wojciech Jaruzelski.
  • 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_69e0b51d8a308190b09113b3b3f9bc15 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8afa1a9b0819083a5a8f34c49d409 completed April 22, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09ad65626c819081615b512241fe1c completed May 17, 2026, 11:58 a.m.
NEDg Description generation batch_6a09b14b7694819084b4b391fa821961 completed May 17, 2026, 12:15 p.m.
NED2 Entity disambiguation (via description) batch_6a09b1af3e708190b7b2971db2508f7b completed May 17, 2026, 12:16 p.m.
Created at: April 16, 2026, 5:07 p.m.