Triple
T22703599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taiwan Provincial Government |
E561385
|
entity |
| Predicate | functionallyStreamlined |
P34990
|
FINISHED |
| Object | 1998 |
—
|
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: 1998 | Statement: [Taiwan Provincial Government, functionallyStreamlined, 1998]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionallyStreamlined Context triple: [Taiwan Provincial Government, functionallyStreamlined, 1998]
-
A.
providesFunctionalityOf
Indicates that one entity supplies, implements, or makes available the capabilities or functions that are normally associated with another entity.
-
B.
organizationalFunction
Indicates the role, purpose, or primary activity that an organization performs within a broader system or context.
-
C.
endedFunctionallyWith
chosen
Indicates that a process, event, or relationship has effectively concluded in practice, even if it has not been formally or officially terminated.
-
D.
기능
Indicates that an entity has a particular function, role, or operational capability.
-
E.
definesFunctioningOf
Indicates that one entity specifies or determines how another entity operates or functions.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cca1e48190bbe7910f13692803 |
completed | April 29, 2026, 3:19 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:16 p.m.