Triple
T2934849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German 17th Army |
E79239
|
entity |
| Predicate | remnants |
P44035
|
FINISHED |
| Object | evacuated by sea from Crimea |
—
|
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: evacuated by sea from Crimea | Statement: [German 17th Army, remnants, evacuated by sea from Crimea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: remnants Context triple: [German 17th Army, remnants, evacuated by sea from Crimea]
-
A.
lastRemnantOf
Indicates that one entity is the sole remaining instance or surviving part of another entity, after all similar or related instances have disappeared.
-
B.
isYoungerRemnantOf
Indicates that one entity is the surviving, younger portion or successor of another entity that existed earlier and has largely disappeared or transformed.
-
C.
housesRemainsOf
Indicates that one entity serves as the location or container in which the physical remains of another entity are kept or preserved.
-
D.
revival
Indicates the act of bringing something back into use, popularity, or active existence after a period of decline, dormancy, or disuse.
-
E.
retained
Indicates that one entity keeps possession, control, or continued engagement of another entity over a period of time.
- 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_69ad8b0fbab081908f6a61567c045d8d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad983c84688190aa7ed5b8091fb140 |
completed | March 8, 2026, 3:39 p.m. |
| PD | Predicate disambiguation | batch_69ad96088fb481909976b436c2b729d9 |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f520208190a4dc43372004555f |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 2:56 p.m.