Triple

T9403407
Position Surface form Disambiguated ID Type / Status
Subject Sergei Witte E226529 entity
Predicate placeOfDeath P21 FINISHED
Object Petrograd E90774 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: Petrograd | Statement: [Sergei Witte, placeOfDeath, Petrograd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petrograd
Context triple: [Sergei Witte, placeOfDeath, Petrograd]
  • A. Mosca
    Mosca is the cunning and manipulative servant in Ben Jonson’s play "Volpone," known for orchestrating deceptions and driving much of the plot’s dark comedy.
  • B. Kirov Leningrad
    Kirov Leningrad was the historic name of the Soviet-era ice hockey club from Leningrad that later became known as SKA Saint Petersburg.
  • C. Pushkino
    Pushkino is a town in Russia that serves as a suburban residential and industrial center northeast of Moscow.
  • D. Leningrad chosen
    Leningrad, now known as Saint Petersburg, is a major Russian city on the Baltic Sea that served as the imperial capital and endured a devastating World War II siege.
  • E. Moscow
    Moscow is the capital and largest city of Russia, serving as its political, economic, and cultural center.
  • 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_69ca843170f88190800a8ab2b5fc568e completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd51bf7e5c8190850b671778496150 completed April 1, 2026, 5:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69d12228d8148190814646881e1f2d98 completed April 4, 2026, 2:37 p.m.
Created at: March 30, 2026, 7:46 p.m.