Triple
T34515662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China Garrison Army |
E886144
|
entity |
| Predicate | natureOfDuties |
P137086
|
FINISHED |
| Object | occupation and security |
—
|
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: occupation and security | Statement: [China Garrison Army, natureOfDuties, occupation and security]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: natureOfDuties Context triple: [China Garrison Army, natureOfDuties, occupation and security]
-
A.
goalOfDuties
Indicates that something is the intended objective or purpose that a set of duties or responsibilities is meant to achieve.
-
B.
scopeOfDuty
chosen
Indicates the range or extent of responsibilities, tasks, or obligations that an entity is expected or authorized to perform.
-
C.
natureOfOffice
Indicates the type or character of an office or position, specifying what kind of role or function it represents.
-
D.
hasDutiesUnder
Indicates that one party is obligated to perform specific responsibilities or fulfill obligations as defined by another party, agreement, or authority.
-
E.
occupationDuty
Indicates that an occupation entails a specific duty, responsibility, or task that is expected to be performed as part of that role.
- 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_69f349ccc290819089d8e82698e53cb6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71fb1ab3881908e2f7c0e6f23db49 |
completed | May 3, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 2:01 a.m.