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.