Triple

T14337322
Position Surface form Disambiguated ID Type / Status
Subject Georg Wilhelm Steller E355497 entity
Predicate placeOfDeath P21 FINISHED
Object Tyumen E232706 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: Tyumen | Statement: [Georg Wilhelm Steller, placeOfDeath, Tyumen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tyumen
Context triple: [Georg Wilhelm Steller, placeOfDeath, Tyumen]
  • A. Tyumen chosen
    Tyumen is a historic city in western Siberia, Russia, known as an early Russian settlement in Siberia and now a major industrial and administrative center.
  • B. Nizhnevartovsk
    Nizhnevartovsk is a major oil-producing city in western Siberia, Russia, known as one of the centers of the country’s petroleum industry.
  • C. Krasnoyarsk
    Krasnoyarsk is a large industrial and cultural city in central Russia, situated on the Yenisei River and known as one of the key urban centers of Siberia.
  • D. Tobolsk
    Tobolsk is a historic Siberian town in Russia known for its Kremlin and as a place of exile and imprisonment during the late imperial period.
  • E. Irkutsk
    Irkutsk is a major city in southeastern Siberia, Russia, historically significant as a political and administrative center and a key hub during the Russian Civil War.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c2241e48190a0c626b3d741966a completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d7c397c81908dab10dd8d7aa367 completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:14 a.m.