Triple

T38157412
Position Surface form Disambiguated ID Type / Status
Subject მიხეილ სააკაშვილი E952922 entity
Predicate ჰყავს მეუღლე P121922 FINISHED
Object სანდრა რულოვსი
სანდრა რულოვსი არის ნიდერლანდური წარმოშობის ქართველი საზოგადო მოღვაწე და საქველმოქმედო აქტივისტი, რომელიც განსაკუთრებით ცნობილია ჯანდაცვისა და ჰუმანიტარული პროექტებით საქართველოში.
 E2257615 NE FINISHED

How this triple was built (3 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: სანდრა რულოვსი | Statement: [მიხეილ სააკაშვილი, ჰყავს მეუღლე, სანდრა რულოვსი]
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: სანდრა რულოვსი
Triple: [მიხეილ სააკაშვილი, ჰყავს მეუღლე, სანდრა რულოვსი]
Generated description
სანდრა რულოვსი არის ნიდერლანდური წარმოშობის ქართველი საზოგადო მოღვაწე და საქველმოქმედო აქტივისტი, რომელიც განსაკუთრებით ცნობილია ჯანდაცვისა და ჰუმანიტარული პროექტებით საქართველოში.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: ჰყავს მეუღლე
Context triple: [მიხეილ სააკაშვილი, ჰყავს მეუღლე, სანდრა რულოვსი]
  • A. الزوجة chosen
    Indicates that one entity is the wife (spouse in a marital relationship) of another entity.
  • B. აქვს შენაკადი
    Indicates that one watercourse serves as a tributary flowing into another watercourse.
  • C. البنت
    Indicates a relationship where an entity is identified as a girl or daughter in relation to another entity.
  • D. تاريخ الزواج
    Indicates the date on which a marriage took place between the related entities.
  • E. הנצחה
    Indicates a relationship where someone or something is commemorated or memorialized so that their memory, deeds, or significance are preserved over time.
  • F. None of above.

Provenance (6 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_69f76f0b93c48190a117319ab3a9f282 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fcb089a8f881909aa9e722babd43f7 completed May 7, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4171397be48190b784c3a8b486ecce completed June 28, 2026, 7:08 p.m.
NEDg Description generation batch_6a4172b1696c8190b1c0ac5c1c2267af completed June 28, 2026, 7:14 p.m.
NED2 Entity disambiguation (via description) batch_6a41732a4d0881908a605d5dd52a3708 completed June 28, 2026, 7:16 p.m.
PD Predicate disambiguation batch_69fc45666c5c8190913bd632ac0e5b84 completed May 7, 2026, 7:55 a.m.
Created at: May 3, 2026, 4:21 p.m.