Triple
T4295417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 6th Army |
E99698
|
entity |
| Predicate | laterOperations |
P38710
|
FINISHED |
| Object | fighting in Ukraine |
—
|
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: fighting in Ukraine | Statement: [6th Army, laterOperations, fighting in Ukraine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterOperations Context triple: [6th Army, laterOperations, fighting in Ukraine]
-
A.
laterWork
Indicates that one work was created, published, or produced after another work in time.
-
B.
finalOperations
Indicates that an entity is involved in the last or concluding set of actions or processes within a sequence or workflow.
-
C.
laterFunction
Indicates that one function or event occurs after another in time.
-
D.
laterActivity
chosen
Indicates that one activity occurs after another in time, establishing a temporal ordering between them.
-
E.
subsequentOperationName
Indicates that one operation occurs later in sequence and is identified by the given subsequent operation name.
- 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35085b864819086cf726285384566 |
completed | March 12, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_69b347fe55a88190b77bab0c0f38e1aa |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:08 p.m.