Triple

T3180608
Position Surface form Disambiguated ID Type / Status
Subject Shlisselburg Fortress E66575 entity
Predicate locatedIn P40 FINISHED
Object Shlisselburg E66575 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: Shlisselburg | Statement: [Shlisselburg Fortress, locatedIn, Shlisselburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shlisselburg
Context triple: [Shlisselburg Fortress, locatedIn, Shlisselburg]
  • A. Shlisselburg chosen
    Shlisselburg is a historic Russian town near Saint Petersburg, best known for its strategic fortress and former political prison on Lake Ladoga.
  • B. Staraya Russa
    Staraya Russa is a historic town in northwestern Russia known for its medieval heritage and mineral spa resorts.
  • C. Gatchina
    Gatchina is a historic Russian town near Saint Petersburg, known for its imperial palace complex and long association with the Romanov dynasty.
  • D. Pskov Kremlin
    The Pskov Kremlin is a historic medieval fortress complex in the city of Pskov, Russia, renowned for its ancient defensive walls, towers, and the Trinity Cathedral.
  • E. Kolomna
    Kolomna is a historic Russian city southeast of Moscow, known for its well-preserved kremlin, medieval architecture, and traditional pastila confectionery.
  • 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_69ad8586a34c8190944c63ec11a8de1a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6a1280c8190b59a2afd30312c02 completed March 8, 2026, 4:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24b7076d48190b614e4b48965e0b4 completed March 12, 2026, 5:13 a.m.
Created at: March 8, 2026, 3:06 p.m.