Triple
T3790937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Third Battle of Kharkov |
E89643
|
entity |
| Predicate | frontLineShift |
P10772
|
FINISHED |
| Object | in favor of Germany in southern sector |
—
|
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: in favor of Germany in southern sector | Statement: [Third Battle of Kharkov, frontLineShift, in favor of Germany in southern sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontLineShift Context triple: [Third Battle of Kharkov, frontLineShift, in favor of Germany in southern sector]
-
A.
frontLineChange
chosen
Indicates a change in the position or configuration of the primary boundary or leading edge between opposing sides.
-
B.
frontLine
Indicates that an entity is positioned at or associated with the foremost or primary line of engagement, activity, or defense relative to others.
-
C.
frontLineBetween
Indicates that a boundary or line of direct confrontation exists separating two opposing sides or regions.
-
D.
frontLineFeature
Indicates that the subject is a prominent or leading characteristic that stands out at the forefront relative to others.
-
E.
frontLineReached
Indicates that an entity has arrived at or crossed into the designated front line or primary boundary of engagement.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecefa3608190a7a20ed6df6a64b2 |
completed | March 9, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69aee743c8d08190a9f9c97b836bd703 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:15 p.m.