Triple

T14022700
Position Surface form Disambiguated ID Type / Status
Subject Victory Park on Sokolovaya Gora E337373 entity
Predicate overlooks P1323 FINISHED
Object city of Saratov E67637 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: city of Saratov | Statement: [Victory Park on Sokolovaya Gora, overlooks, city of Saratov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Saratov
Context triple: [Victory Park on Sokolovaya Gora, overlooks, city of Saratov]
  • A. Saratov chosen
    Saratov is a major city in southwestern Russia known as an important cultural, educational, and industrial center on the banks of the Volga River.
  • B. city of Rostov
    The city of Rostov is one of Russia’s oldest historic towns, renowned for its well-preserved kremlin and significant role in the cultural heritage of the Golden Ring region.
  • C. Ulyanovka
    Ulyanovka is an urban-type settlement in Leningrad Oblast, Russia, situated within the administrative boundaries of Tosnensky District.
  • D. Ulyanov
    Ulyanov is the Russian surname of Vladimir Lenin, the revolutionary leader and founder of the Soviet state.
  • E. Rostov
    Rostov is one of Russia’s oldest and most historically significant towns, renowned for its well-preserved kremlin and traditional architecture.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2f3d87b88190b038d334f4965369 completed April 14, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb655bb34819097fe88ba76464be8 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:19 p.m.