Triple

T5232848
Position Surface form Disambiguated ID Type / Status
Subject Chinese imperial examination system E118150 entity
Predicate lowerDegree P11456 FINISHED
Object shengyuan
Shengyuan was the lowest scholarly degree in imperial China’s examination system, designating entry-level licentiates eligible for further civil service exams.
E504971 NE FINISHED

How this triple was built (5 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: shengyuan | Statement: [Chinese imperial examination system, lowerDegree, shengyuan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: shengyuan
Context triple: [Chinese imperial examination system, lowerDegree, shengyuan]
  • A. Shuheng
    Shuheng is the given name of He Shuheng, an early Chinese Communist revolutionary and political figure.
  • B. Zheyuan
    Zheyuan is a given name most notably borne by the Chinese general and politician Song Zheyuan.
  • C. Zhenyuan
    Zhenyuan was a late 19th-century Chinese ironclad battleship of the Beiyang Fleet that played a prominent role in the First Sino-Japanese War.
  • D. Shëngjin
    Shëngjin is a coastal town and port in northwestern Albania on the Adriatic Sea, historically significant for its strategic maritime position.
  • E. Shiing-Shen
    Shiing-Shen Chern was a Chinese-American mathematician renowned for his foundational contributions to differential geometry and the development of Chern classes in topology.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: shengyuan
Triple: [Chinese imperial examination system, lowerDegree, shengyuan]
Generated description
Shengyuan was the lowest scholarly degree in imperial China’s examination system, designating entry-level licentiates eligible for further civil service exams.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: shengyuan
Target entity description: Shengyuan was the lowest scholarly degree in imperial China’s examination system, designating entry-level licentiates eligible for further civil service exams.
  • A. Shuheng
    Shuheng is the given name of He Shuheng, an early Chinese Communist revolutionary and political figure.
  • B. Zheyuan
    Zheyuan is a given name most notably borne by the Chinese general and politician Song Zheyuan.
  • C. Zhenyuan
    Zhenyuan was a late 19th-century Chinese ironclad battleship of the Beiyang Fleet that played a prominent role in the First Sino-Japanese War.
  • D. Shëngjin
    Shëngjin is a coastal town and port in northwestern Albania on the Adriatic Sea, historically significant for its strategic maritime position.
  • E. Shiing-Shen
    Shiing-Shen Chern was a Chinese-American mathematician renowned for his foundational contributions to differential geometry and the development of Chern classes in topology.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: lowerDegree
Context triple: [Chinese imperial examination system, lowerDegree, shengyuan]
  • A. lowerRank chosen
    Indicates that one entity holds an inferior or subordinate rank, status, or position relative to another entity.
  • B. lowestCategory
    Indicates that an entity belongs to the most specific or least general category within a classification hierarchy.
  • C. lowestRank
    Indicates that the subject has the least or worst rank in an ordered set compared to all other related entities.
  • D. lowerValueIndicates
    Indicates that a smaller numerical value of a property or measurement corresponds to a greater degree, better outcome, or stronger presence of the relevant characteristic.
  • E. lowerRankDescription
    Indicates that one entity holds a lower rank or status in a hierarchy relative to another entity.
  • F. None of above.

Provenance (6 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.
NED1 Entity disambiguation (via context triple) batch_69bef8154940819098ed76e14804f4b3 completed March 21, 2026, 7:57 p.m.
NEDg Description generation batch_69bef8bfcd1c819090b81f8ebb097c5b completed March 21, 2026, 8 p.m.
NED2 Entity disambiguation (via description) batch_69bef95e7ce48190a1ec2fc27ce37d00 completed March 21, 2026, 8:02 p.m.
PD Predicate disambiguation batch_69bd77bf1ef08190bb3487b3f3ee088c completed March 20, 2026, 4:37 p.m.
Created at: March 20, 2026, 1:49 p.m.