Triple

T1524324
Position Surface form Disambiguated ID Type / Status
Subject Ma E32300 entity
Predicate notableBearer P458 FINISHED
Object Ma Kai
Ma Kai is a Chinese politician who served as a Vice Premier of the State Council and played a key role in the country’s economic and financial policymaking.
E175090 NE FINISHED

How this triple was built (4 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: Ma Kai | Statement: [Ma, notableBearer, Ma Kai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ma Kai
Context triple: [Ma, notableBearer, Ma Kai]
  • A. Shiso
    Shiso is a small inland city in Japan’s Hyogo Prefecture known for its mountainous scenery, forests, and outdoor recreation.
  • B. Zestaponi
    Zestaponi is an industrial town in western Georgia known historically for its manganese processing and role as a regional transport hub.
  • C. Maki
    Maki is a Japanese surname most notably associated with Fumihiko Maki, a prominent modernist architect known for his innovative urban and architectural designs.
  • D. Tokyo Chiken
    Tokyo Chiken is the commonly used abbreviated name for the Tokyo District Public Prosecutors Office, a key prosecutorial authority in Japan’s capital.
  • E. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • 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: Ma Kai
Triple: [Ma, notableBearer, Ma Kai]
Generated description
Ma Kai is a Chinese politician who served as a Vice Premier of the State Council and played a key role in the country’s economic and financial policymaking.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ma Kai
Target entity description: Ma Kai is a Chinese politician who served as a Vice Premier of the State Council and played a key role in the country’s economic and financial policymaking.
  • A. Shiso
    Shiso is a small inland city in Japan’s Hyogo Prefecture known for its mountainous scenery, forests, and outdoor recreation.
  • B. Zestaponi
    Zestaponi is an industrial town in western Georgia known historically for its manganese processing and role as a regional transport hub.
  • C. Maki
    Maki is a Japanese surname most notably associated with Fumihiko Maki, a prominent modernist architect known for his innovative urban and architectural designs.
  • D. Tokyo Chiken
    Tokyo Chiken is the commonly used abbreviated name for the Tokyo District Public Prosecutors Office, a key prosecutorial authority in Japan’s capital.
  • E. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • F. None of above. chosen

Provenance (5 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_69a885e9b0ac819093a9806ad0efc82c completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9080175588190bb3b1d4b17966f2f completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad2951c1ec8190b7ac04cd820a2bfa completed March 8, 2026, 7:46 a.m.
NEDg Description generation batch_69ad2d3e2b388190a73f2604d97bb4aa completed March 8, 2026, 8:03 a.m.
NED2 Entity disambiguation (via description) batch_69ad2df61a70819094148563f924a5c5 completed March 8, 2026, 8:06 a.m.
Created at: March 4, 2026, 7:26 p.m.