Triple
T10235951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Volkhov Front |
E243462
|
entity |
| Predicate | frontLineLengthApprox |
P38466
|
FINISHED |
| Object | several hundred kilometers |
—
|
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: several hundred kilometers | Statement: [Volkhov Front, frontLineLengthApprox, several hundred kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontLineLengthApprox Context triple: [Volkhov Front, frontLineLengthApprox, several hundred kilometers]
-
A.
frontLineLength
chosen
Indicates the total measured extent of the front line where opposing forces or boundaries directly face each other.
-
B.
queueLength
Indicates the current number of items or entities waiting in a queue.
-
C.
frontLineNear
Indicates that one entity is located close to the primary boundary or front line associated with another entity.
-
D.
frontLineReached
Indicates that an entity has arrived at or crossed into the designated front line or primary boundary of engagement.
-
E.
frontLength
Indicates the length measurement of the front side or edge of an object relative to its overall dimensions.
- 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d23b620c8190b8a72d0eb0d16b93 |
completed | April 7, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69d4d1e9798c8190b437d53d48554ba1 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:22 a.m.