Triple
T9827886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Encirclement of Leningrad from the south and southwest |
E238703
|
entity |
| Predicate | directionOfEncirclement |
P90222
|
FINISHED |
| Object | south |
—
|
LITERAL 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: south | Statement: [Encirclement of Leningrad from the south and southwest, directionOfEncirclement, south]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionOfEncirclement Context triple: [Encirclement of Leningrad from the south and southwest, directionOfEncirclement, south]
-
A.
encircledForce
Indicates that a military force is surrounded by enemy units, cutting off its movement or escape routes.
-
B.
encirclementOperation
Indicates a military action in which forces maneuver to surround an opposing force, cutting off its escape routes and lines of support.
-
C.
tacticalFormation
Indicates a specific strategic arrangement or positioning of entities relative to one another to achieve a tactical objective.
-
D.
surroundedOnThreeSidesBy
Indicates that one entity is positioned so that three of its sides are directly bordered or enclosed by another entity.
-
E.
surrounds
Indicates that one entity is located all around another entity, enclosing or encircling it on multiple sides or completely.
- F. None of above. chosen
Provenance (4 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_69ca84e0dd1881909800765d1e21f735 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb324e7848190b9424a78ca653afe |
completed | April 2, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cd03e30bc08190816c0a6d29c21b0f |
completed | April 1, 2026, 11:39 a.m. |
| PDg | Predicate description generation | batch_69cd06abc9248190a506b64e9c516d03 |
completed | April 1, 2026, 11:51 a.m. |
Created at: March 30, 2026, 8:32 p.m.