Triple

T19485916
Position Surface form Disambiguated ID Type / Status
Subject Mirga Gražinytė-Tyla E487510 entity
Predicate parent P120 FINISHED
Object Aušra Gražinytė
Aušra Gražinytė is the mother of renowned Lithuanian conductor Mirga Gražinytė-Tyla.
E1387244 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: Aušra Gražinytė | Statement: [Mirga Gražinytė-Tyla, parent, Aušra Gražinytė]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aušra Gražinytė
Context triple: [Mirga Gražinytė-Tyla, parent, Aušra Gražinytė]
  • A. Gintarė Venčkauskaitė
    Gintarė Venčkauskaitė is a Lithuanian modern pentathlete who has represented Lithuania at the Olympic Games.
  • B. Aurika Sereikaitė
    Aurika Sereikaitė is a Lithuanian speed skater who has represented Lithuania in multiple Winter Olympic Games.
  • C. Irena Degutienė
    Irena Degutienė is a Lithuanian politician who has served in prominent leadership roles in the national parliament and is associated with the conservative Homeland Union party.
  • D. Rūta Meilutytė
    Rūta Meilutytė is a Lithuanian swimmer and Olympic champion best known for winning gold in the 100m breaststroke at the 2012 London Games as a teenager.
  • E. Daina Gudzinevičiūtė
    Daina Gudzinevičiūtė is a Lithuanian sport shooter and Olympic champion, best known for winning gold in women’s trap at the 2000 Sydney Games and later serving in sports administration.
  • 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: Aušra Gražinytė
Triple: [Mirga Gražinytė-Tyla, parent, Aušra Gražinytė]
Generated description
Aušra Gražinytė is the mother of renowned Lithuanian conductor Mirga Gražinytė-Tyla.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Aušra Gražinytė
Target entity description: Aušra Gražinytė is the mother of renowned Lithuanian conductor Mirga Gražinytė-Tyla.
  • A. Gintarė Venčkauskaitė
    Gintarė Venčkauskaitė is a Lithuanian modern pentathlete who has represented Lithuania at the Olympic Games.
  • B. Aurika Sereikaitė
    Aurika Sereikaitė is a Lithuanian speed skater who has represented Lithuania in multiple Winter Olympic Games.
  • C. Irena Degutienė
    Irena Degutienė is a Lithuanian politician who has served in prominent leadership roles in the national parliament and is associated with the conservative Homeland Union party.
  • D. Rūta Meilutytė
    Rūta Meilutytė is a Lithuanian swimmer and Olympic champion best known for winning gold in the 100m breaststroke at the 2012 London Games as a teenager.
  • E. Daina Gudzinevičiūtė
    Daina Gudzinevičiūtė is a Lithuanian sport shooter and Olympic champion, best known for winning gold in women’s trap at the 2000 Sydney Games and later serving in sports administration.
  • 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_69d8e8d924388190b847cb15bb3d0aff completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6343f46e88190b7ba65c210285bee completed April 20, 2026, 2:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07719e60a48190bf4c54af72900b87 completed May 15, 2026, 7:18 p.m.
NEDg Description generation batch_6a07780c685881909b3926b75baa01f2 completed May 15, 2026, 7:46 p.m.
NED2 Entity disambiguation (via description) batch_6a0778c1cfb881909ab613cd4e125120 completed May 15, 2026, 7:49 p.m.
Created at: April 10, 2026, 1:39 p.m.