Triple
T19042258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Army Group C |
E466033
|
entity |
| Predicate | initialTask |
P63932
|
FINISHED |
| Object | defense of Germany’s western border in 1939–1940 |
—
|
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: defense of Germany’s western border in 1939–1940 | Statement: [Army Group C, initialTask, defense of Germany’s western border in 1939–1940]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialTask Context triple: [Army Group C, initialTask, defense of Germany’s western border in 1939–1940]
-
A.
primaryTask
Indicates that an entity has a main or most important task, role, or function it is responsible for above all others.
-
B.
initialAction
Indicates the first or starting action taken in a sequence of actions or events.
-
C.
firstProgramTask
Indicates that an action or task is the initial or earliest program-related task undertaken in a sequence.
-
D.
initialGoal
chosen
Indicates that something represents the first or starting objective or target in a sequence of goals.
-
E.
targetTask
Indicates that one entity is the specific task or objective that another entity is aiming to perform, achieve, or operate on.
- 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d801ef188190a231e85e1bbce037 |
completed | April 20, 2026, 7:38 a.m. |
| PD | Predicate disambiguation | batch_69e4b99633c8819097988608c278ecf8 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:03 p.m.