Triple
T19819118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shevardino Redoubt area |
E476138
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object |
Shevardino
Shevardino is a village in Russia historically associated with the Battle of Borodino during Napoleon’s 1812 invasion.
|
E1397155
|
NE FINISHED |
How this triple was built (4 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: Shevardino | Statement: [Shevardino Redoubt area, nearbySettlement, Shevardino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shevardino Context triple: [Shevardino Redoubt area, nearbySettlement, Shevardino]
-
A.
Meskheti
Meskheti is a historical region in southwestern Georgia known for its mountainous landscapes, strategic location along ancient trade routes, and culturally diverse heritage.
-
B.
Skvira
Skvira is a town in Ukraine historically associated with the Skver Hasidic dynasty and its Jewish community.
-
C.
Bazaleti
Bazaleti is a village in eastern Georgia known for its scenic Bazaleti Lake and location within the Dusheti Municipality of the Mtskheta-Mtianeti region.
-
D.
Dusheti
Dusheti is a small historic town in eastern Georgia known for its mountainous surroundings and traditional architecture.
-
E.
Shekvetili
Shekvetili is a coastal village and resort area on Georgia’s Black Sea shore, known for its beaches, pine forests, and cultural attractions.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Shevardino Triple: [Shevardino Redoubt area, nearbySettlement, Shevardino]
Generated description
Shevardino is a village in Russia historically associated with the Battle of Borodino during Napoleon’s 1812 invasion.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Shevardino Target entity description: Shevardino is a village in Russia historically associated with the Battle of Borodino during Napoleon’s 1812 invasion.
-
A.
Meskheti
Meskheti is a historical region in southwestern Georgia known for its mountainous landscapes, strategic location along ancient trade routes, and culturally diverse heritage.
-
B.
Skvira
Skvira is a town in Ukraine historically associated with the Skver Hasidic dynasty and its Jewish community.
-
C.
Bazaleti
Bazaleti is a village in eastern Georgia known for its scenic Bazaleti Lake and location within the Dusheti Municipality of the Mtskheta-Mtianeti region.
-
D.
Dusheti
Dusheti is a small historic town in eastern Georgia known for its mountainous surroundings and traditional architecture.
-
E.
Shekvetili
Shekvetili is a coastal village and resort area on Georgia’s Black Sea shore, known for its beaches, pine forests, and cultural attractions.
- F. None of above. chosen
Provenance (5 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e654fc8b94819095fd5240f33b6713 |
completed | April 20, 2026, 4:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ccce7d0881909a08ef7e52078998 |
completed | May 16, 2026, 1:47 a.m. |
| NEDg | Description generation | batch_6a07cf8ca2988190b2dfa8c2f4d3dcd9 |
completed | May 16, 2026, 1:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07d02ee2308190b263ed90342e9072 |
completed | May 16, 2026, 2:02 a.m. |
Created at: April 10, 2026, 1:50 p.m.