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.