Triple
T5232866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese imperial examination system |
E118150
|
entity |
| Predicate | typicalQuestionType |
P12351
|
FINISHED |
| Object | policy essay |
—
|
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: policy essay | Statement: [Chinese imperial examination system, typicalQuestionType, policy essay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalQuestionType Context triple: [Chinese imperial examination system, typicalQuestionType, policy essay]
-
A.
questionType
chosen
Indicates the specific category or kind of question that an item, query, or prompt belongs to.
-
B.
questionnaireType
Indicates the specific category or kind of questionnaire associated with an entity or interaction.
-
C.
questionText
Indicates the textual content of a question as it is posed or displayed.
-
D.
guidingQuestionOf
Indicates that one item serves as a guiding or central question that frames, directs, or structures another item (such as a discussion, activity, or work).
-
E.
questionForm
Indicates that one entity is expressed or structured in the form of a question directed toward another entity or context.
- 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_69bd4466fb8c819083b806a79414d7e4 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b0389048190b55b7c44fe657044 |
completed | March 20, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69bd77bf1ef08190bb3487b3f3ee088c |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:49 p.m.