Triple
T5232842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese imperial examination system |
E118150
|
entity |
| Predicate | hadLevel |
P2393
|
FINISHED |
| Object | prefectural examination |
—
|
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: prefectural examination | Statement: [Chinese imperial examination system, hadLevel, prefectural examination]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadLevel Context triple: [Chinese imperial examination system, hadLevel, prefectural examination]
-
A.
hasLevel
chosen
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
-
B.
levels
Indicates that one entity adjusts, equalizes, or smooths out the height, intensity, or degree of another entity.
-
C.
playedAtLevel
Indicates that an entity participated or performed in an activity, event, or game at a specified level of difficulty, competition, or hierarchy.
-
D.
affectedLevel
Indicates the degree or extent to which one entity is impacted or influenced by another entity or event.
-
E.
hadNo
Indicates that one entity completely lacked or did not possess another entity, attribute, or relationship.
- 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.