Triple

T10669147
Position Surface form Disambiguated ID Type / Status
Subject Alexander Alexandrov E251438 entity
Predicate familyName P18 FINISHED
Object Alexandrov E471233 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: Alexandrov | Statement: [Alexander Alexandrov, familyName, Alexandrov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alexandrov
Context triple: [Alexander Alexandrov, familyName, Alexandrov]
  • A. Alexandrov chosen
    Alexandrov is a historic Russian town in Vladimir Oblast, known for its former status as a royal residence and its well-preserved architectural heritage.
  • B. Alexandrovsk
    Alexandrovsk was a historical town in the Russian Empire, now known as Zaporizhzhia in southeastern Ukraine.
  • C. Pavel Alexandrov
    Pavel Alexandrov was a prominent Russian-Soviet mathematician known for his foundational contributions to topology and his role in developing the Moscow school of mathematics.
  • D. Alexandrovich
    Alexandrovich is the Russian patronymic indicating "son of Alexander," famously used in the full name of Tsar Nicholas II of Russia.
  • E. Alekseyev
    Alekseyev is a Russian surname borne by various notable figures in Russian history, military, and culture.
  • 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_69d6aa5b0d2881909584b20efc5877f0 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6f861513881909b44c711371086b7 completed April 9, 2026, 12:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69d97a9e722c8190a5d9f728282b9a52 completed April 10, 2026, 10:33 p.m.
Created at: April 8, 2026, 9:09 p.m.