Triple

T10108912
Position Surface form Disambiguated ID Type / Status
Subject White forces E218191 entity
Predicate hasPart P35 FINISHED
Object Don Cossacks E229103 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: Don Cossacks | Statement: [White forces, hasPart, Don Cossacks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Cossacks
Context triple: [White forces, hasPart, Don Cossacks]
  • A. Don Cossacks chosen
    The Don Cossacks are a historic Cossack community that formed a semi-autonomous, militarized society along the Don River in southern Russia, renowned for their cavalry, frontier service, and distinctive culture.
  • B. Krymchaks
    Krymchaks are a historically Turkic-speaking Jewish ethnic group from Crimea, known for their distinct religious traditions and unique blend of Turkic and Jewish cultural heritage.
  • C. Shchors
    Shchors is a 1939 Soviet biographical war film directed by Alexander Dovzhenko about the Ukrainian Bolshevik commander Nikolai Shchors.
  • D. Solyony
    Solyony is a volatile and eccentric army officer in Anton Chekhov’s play "Three Sisters," known for his morbid humor and ultimately tragic duel.
  • E. Russy
    Russy is a small municipality located in the Broye district of the canton of Fribourg in western Switzerland.
  • 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_69ca83da93fc8190b54e44bc2b34857c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd0cbd8a48190b2af6177d1249f58 completed April 2, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2e59ec83c8190a79fbb0d0de90310 completed April 5, 2026, 10:43 p.m.
Created at: March 30, 2026, 9:03 p.m.