Triple
T17482118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First U.S. Army Group |
E425685
|
entity |
| Predicate | hadSubordinateUnit |
P71417
|
FINISHED |
| Object | fictitious U.S. divisions |
—
|
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: fictitious U.S. divisions | Statement: [First U.S. Army Group, hadSubordinateUnit, fictitious U.S. divisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadSubordinateUnit Context triple: [First U.S. Army Group, hadSubordinateUnit, fictitious U.S. divisions]
-
A.
subsidiaryUnit
Indicates that one organizational unit functions as a subordinate or dependent division of another, higher-level unit.
-
B.
successorSubunit
Indicates that one organizational subunit is the direct successor or continuation of another subunit in a structural or temporal sequence.
-
C.
hasSubunits
chosen
Indicates that an entity is composed of or organized into smaller constituent units that are part of its structure.
-
D.
formerSubunit
Indicates that one entity was previously a subunit or subordinate part of another entity, but no longer holds that status.
-
E.
subunitOf
Indicates that one entity functions as a component or smaller part within the structure or organization of another, larger entity.
- 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451c0db14819098922453131fb40a |
completed | April 19, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f341c88190adabe526d8903b05 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:48 a.m.