Triple
T15644680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 監察院 |
E376147
|
entity |
| Predicate | canRequestDocumentsFrom |
P20806
|
FINISHED |
| Object | 各級政府機關 |
—
|
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: 各級政府機關 | Statement: [監察院, canRequestDocumentsFrom, 各級政府機關]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRequestDocumentsFrom Context triple: [監察院, canRequestDocumentsFrom, 各級政府機關]
-
A.
mayRequest
chosen
Indicates that one entity is permitted or authorized to make a request to another entity or for a particular resource or action.
-
B.
hasNotableDocument
Indicates that an entity is associated with a document that is considered significant, noteworthy, or of particular importance.
-
C.
canTakeForm
Indicates that one entity is capable of assuming, transforming into, or being represented as the form or appearance of another entity.
-
D.
requiresDocument
Indicates that one entity can only proceed, be valid, or be completed if a specified document is provided or present.
-
E.
hasOfficialDocument
Indicates that an entity possesses or is associated with a formal, authorized document issued by a recognized authority.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ed400ec8190a14a9f7cf3092865 |
completed | April 16, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69deda890140819082608931e993dd61 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:15 a.m.