Triple
T13626709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Izium salient |
E325600
|
entity |
| Predicate | frontStatus |
P111360
|
FINISHED |
| Object | contested area between Soviet and German armies |
—
|
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: contested area between Soviet and German armies | Statement: [Izium salient, frontStatus, contested area between Soviet and German armies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontStatus Context triple: [Izium salient, frontStatus, contested area between Soviet and German armies]
-
A.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
B.
frontOf
Indicates that one entity is positioned directly before another along a primary viewing or movement direction.
-
C.
front
Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
-
D.
frontLevel
Indicates a relationship where one entity is positioned at or aligned with the foremost or leading level relative to another reference point or structure.
-
E.
frontHeld
Indicates that one entity is being held in front of another entity or reference point.
- F. None of above. chosen
Provenance (4 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_69d8076aae28819092cf636190ee5529 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc60635d08190899806fe8936f02a |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe85e1c4819095194f4b7f9f6118 |
completed | April 12, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69dbc6043e148190a2a25f929cfa35e5 |
completed | April 12, 2026, 4:19 p.m. |
Created at: April 9, 2026, 9:51 p.m.