Triple

T9246221
Position Surface form Disambiguated ID Type / Status
Subject Mátyás Rákosi E222201 entity
Predicate placeOfDeath P21 FINISHED
Object Gorky E350714 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: Gorky | Statement: [Mátyás Rákosi, placeOfDeath, Gorky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gorky
Context triple: [Mátyás Rákosi, placeOfDeath, Gorky]
  • A. Gorky chosen
    Gorky is the former name of the Russian city of Nizhny Novgorod, historically known as a closed city in the Soviet era and a site of internal exile for dissidents.
  • B. Maksim Gorky
    Maksim Gorky was a seminal Russian and Soviet writer, socialist realist pioneer, and political activist whose works and public life profoundly influenced 20th-century Russian literature and culture.
  • C. Rozhdestvensky
    Rozhdestvensky is a Russian surname most notably associated with figures such as conductor Gennady Rozhdestvensky.
  • D. Zakhar Moglin
    Zakhar Moglin was the husband of Zinaida Volkova, the daughter of Russian revolutionary Leon Trotsky.
  • E. Mikhail Bulgakov-Golitsa
    Mikhail Bulgakov-Golitsa was a 16th-century Russian military leader and nobleman of the Grand Duchy of Moscow, noted for his role in major conflicts with the Grand Duchy of Lithuania and Poland.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd03f181e081908d9ff7dc6f86420e completed April 1, 2026, 11:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1077d8a048190b4b45419fb0d7279 completed April 4, 2026, 12:43 p.m.
Created at: March 30, 2026, 7:30 p.m.