Triple
T4585832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yunnan Army |
E101964
|
entity |
| Predicate | hadSubunit |
P28620
|
FINISHED |
| Object | provincial infantry units |
—
|
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: provincial infantry units | Statement: [Yunnan Army, hadSubunit, provincial infantry units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadSubunit Context triple: [Yunnan Army, hadSubunit, provincial infantry units]
-
A.
subunitOf
chosen
Indicates that one entity functions as a component or smaller part within the structure or organization of another, larger entity.
-
B.
formerSubunit
Indicates that one entity was previously a subunit or subordinate part of another entity, but no longer holds that status.
-
C.
hasSubunitName
Indicates that an entity includes or is associated with a named subunit or component as part of its structure or organization.
-
D.
subunitType
Indicates that one entity is a specific kind or classification of subunit within the structure or composition of another entity.
-
E.
subsidiaryUnit
Indicates that one organizational unit functions as a subordinate or dependent division of another, higher-level unit.
- 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_69bd43d4ce208190b53158c882b222e3 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5906a43c81908fb11bf8f94be122 |
completed | March 20, 2026, 2:26 p.m. |
| PD | Predicate disambiguation | batch_69bd522acbcc8190bf24d9517793a2c1 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:10 p.m.