Triple
T16895685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soviet 3rd Shock Army |
E424293
|
entity |
| Predicate | frontlineAdvanceDirection |
P13445
|
FINISHED |
| Object | towards Berlin |
—
|
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: towards Berlin | Statement: [Soviet 3rd Shock Army, frontlineAdvanceDirection, towards Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontlineAdvanceDirection Context triple: [Soviet 3rd Shock Army, frontlineAdvanceDirection, towards Berlin]
-
A.
frontLineDirection
chosen
Indicates the primary orientation or bearing in which the front line of a conflict, formation, or boundary is facing or advancing.
-
B.
frontLineNear
Indicates that one entity is located close to the primary boundary or front line associated with another entity.
-
C.
frontLine
Indicates that an entity is positioned at or associated with the foremost or primary line of engagement, activity, or defense relative to others.
-
D.
frontLineBetween
Indicates that a boundary or line of direct confrontation exists separating two opposing sides or regions.
-
E.
frontlineCommand
Indicates a command relationship where one entity directs or controls operations at the front line of an activity, conflict, or mission.
- 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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3c8d7aec88190888f13601acbcd77 |
completed | April 18, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69e32b90ec3c819099c51bb7baf2984c |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.