Triple
T17504340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhu Zaiji |
E426271
|
entity |
| Predicate | courtReform |
P4888
|
FINISHED |
| Object | recalled capable officials dismissed under Jiajing |
—
|
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: recalled capable officials dismissed under Jiajing | Statement: [Zhu Zaiji, courtReform, recalled capable officials dismissed under Jiajing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtReform Context triple: [Zhu Zaiji, courtReform, recalled capable officials dismissed under Jiajing]
-
A.
courtReview
Indicates that a court formally examines a decision, action, or case to determine its legality, correctness, or appropriateness.
-
B.
reform
chosen
Indicates bringing about significant changes to an existing system, practice, or entity in order to improve or correct it.
-
C.
courtFunction
Indicates that one entity serves as a judicial body or performs an official judicial role or function in relation to another entity or context.
-
D.
legalReformer
Indicates that an entity works to change, improve, or modernize laws or legal systems.
-
E.
courts
Indicates that one entity actively seeks the favor, support, or romantic interest of another through deliberate actions or overtures.
- 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_69d889dd9164819087b1dc3c9240c870 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45214d44c8190b1bf04bf24ab8e81 |
completed | April 19, 2026, 3:55 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f5fbcc8190a6ea9639bf5650da |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:48 a.m.