Triple
T11043047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kramatorsk |
E261065
|
entity |
| Predicate | wasRetakenBy |
P34167
|
FINISHED |
| Object | Armed Forces of Ukraine in 2014 |
—
|
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: Armed Forces of Ukraine in 2014 | Statement: [Kramatorsk, wasRetakenBy, Armed Forces of Ukraine in 2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasRetakenBy Context triple: [Kramatorsk, wasRetakenBy, Armed Forces of Ukraine in 2014]
-
A.
wasRecapturedBy
chosen
Indicates that an entity which had previously escaped or been released was caught again by another entity.
-
B.
reoccupiedByUnionForces
Indicates that a location previously held by Union forces was retaken and brought back under Union military control.
-
C.
laterGarrisonedBy
Indicates that a location or structure was subsequently occupied and used as a military garrison by a specified force or group.
-
D.
afterConquestBy
Indicates that one entity exists in a state, condition, or situation that occurs subsequent to and as a result of being conquered by another entity.
-
E.
reoccupiedIn
Indicates that an entity came back to occupy or take control of a place or position again at a specified time or during a specified period.
- F. None of above.
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_69d6aa979bdc8190bf0e79104cc098c1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7982d42bc81908ac10f54a7b43fb7 |
completed | April 9, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_69d74407cb088190ba37c8da3d342b64 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.