Triple

T8335193
Position Surface form Disambiguated ID Type / Status
Subject Anna Larina E195169 entity
Predicate name P16 FINISHED
Object Anna Larina E195169 NE FINISHED

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: Anna Larina | Statement: [Anna Larina, name, Anna Larina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Larina
Context triple: [Anna Larina, name, Anna Larina]
  • A. Anna Larina chosen
    Anna Larina was a Soviet memoirist and political figure best known for her efforts to rehabilitate the legacy of her husband, Bolshevik leader Nikolai Bukharin, after his execution during Stalin’s purges.
  • B. Lillian Langdon
    Lillian Langdon was an American silent film actress active in the early 20th century, known for her character roles in numerous dramas and melodramas.
  • C. Rose Allerton
    Rose Allerton was a member of the early 17th-century Allerton family associated with the Pilgrim settlers of Plymouth Colony.
  • D. Jane Sidey
    Jane Sidey is known primarily as the wife of acclaimed British film composer John Barry.
  • E. Rosalie Poe
    Rosalie Poe was the younger sister of American writer Edgar Allan Poe, known primarily for her familial connection to the famous author and the mystery surrounding her parentage and early life.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82e87f2c8190bdb71ee29dfc642d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7fd2ca648190991e398ba70caf8d completed March 31, 2026, 8:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95d9b92c8190b1eb0e64aa7ea59e completed April 1, 2026, 10:02 p.m.
Created at: March 30, 2026, 5:57 p.m.