Triple

T30713997
Position Surface form Disambiguated ID Type / Status
Subject Natalia Alianovna Romanova E781970 entity
Predicate mcuFosterFamilyMember P170059 FINISHED
Object Yelena Belova NE NERFINISHED

How this triple was built (2 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: Yelena Belova | Statement: [Natalia Alianovna Romanova, mcuFosterFamilyMember, Yelena Belova]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mcuFosterFamilyMember
Context triple: [Natalia Alianovna Romanova, mcuFosterFamilyMember, Yelena Belova]
  • A. fosterParents
    Indicates a relationship where individuals act as temporary parental caregivers for a child who is not their biological or adopted offspring.
  • B. fosterMother
    Indicates a parental relationship where a woman temporarily cares for and raises a child who is not biologically her own, typically through a formal fostering arrangement.
  • C. fosterChild
    Indicates a relationship where one person is the child being cared for and raised by foster parents who are not their biological or legal parents.
  • D. hasFosterFamily
    Indicates that an entity is placed with and cared for by a foster family, rather than its original or biological family.
  • E. fosteredAt
    Indicates that an entity is being or has been cared for or temporarily housed at a particular foster location or institution.
  • F. None of above. chosen

Provenance (4 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_69f224acd24481908ed5f96f0d69b5dd completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f68c20d09481908f566241722507d3 completed May 2, 2026, 11:43 p.m.
PD Predicate disambiguation batch_69f6861170d08190bb98be609d436f84 completed May 2, 2026, 11:17 p.m.
PDg Predicate description generation batch_69f688034580819086a0f9100645f8ba completed May 2, 2026, 11:25 p.m.
Created at: April 29, 2026, 8:35 p.m.