Triple
T5670209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Courland Pocket |
E124955
|
entity |
| Predicate | numberOfGermanTroops |
P6153
|
FINISHED |
| Object | approximately 200000 |
—
|
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: approximately 200000 | Statement: [Courland Pocket, numberOfGermanTroops, approximately 200000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfGermanTroops Context triple: [Courland Pocket, numberOfGermanTroops, approximately 200000]
-
A.
numberOfTroopsInvolved
chosen
Indicates the quantity of military personnel participating in or assigned to a specific operation, event, or engagement.
-
B.
germanUnit
Indicates that an entity is a military or organizational unit that belongs to, originates from, or is associated with Germany.
-
C.
PrussianStrength
Indicates a relationship where an entity possesses or exhibits the military, political, or institutional power characteristic of Prussia.
-
D.
troopStrengthAlliedApprox
Indicates that the approximate troop strength of one entity is being assessed or reported in relation to its allied forces.
-
E.
numberOfGermanVictims
Indicates the quantity of victims who are identified as German in the context of the described event or situation.
- 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_69c00828906881908966f270b8f130cf |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c025303860819093e51f176babed71 |
completed | March 22, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_69c021bc3894819084f37d14ba4b2644 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:43 p.m.