Triple

T18760512
Position Surface form Disambiguated ID Type / Status
Subject Central Academy of Fine Arts E458757 entity
Predicate shortName P43 FINISHED
Object CAFA
CAFA is a leading Chinese art academy renowned for its rigorous fine arts education and influential role in contemporary Chinese art.
 E1342105 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: CAFA | Statement: [Central Academy of Fine Arts, shortName, CAFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CAFA
Context triple: [Central Academy of Fine Arts, shortName, CAFA]
  • A. CAFA
    CAFA is a U.S. federal law that expanded federal jurisdiction over large class action lawsuits to address perceived abuses in state courts.
  • B. CAFA
    CAFA (Central Asian Football Association) is the regional governing body for football in Central Asia under the Asian Football Confederation (AFC).
  • C. CAFAM
    CAFAM is a Los Angeles museum dedicated to contemporary craft, art, and design, showcasing innovative works in ceramics, fiber, wood, and other materials.
  • D. CAFF
    CAFF is an Arctic Council working group focused on the conservation and sustainable use of Arctic biodiversity, ecosystems, and related natural resources.
  • E. UCCA
    UCCA is a New York State statute that governs the organization, jurisdiction, and procedures of the state's city courts.
  • 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: CAFA
Triple: [Central Academy of Fine Arts, shortName, CAFA]
Generated description
CAFA is a leading Chinese art academy renowned for its rigorous fine arts education and influential role in contemporary Chinese art.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CAFA
Target entity description: CAFA is a leading Chinese art academy renowned for its rigorous fine arts education and influential role in contemporary Chinese art.
  • A. CAFA
    CAFA is a U.S. federal law that expanded federal jurisdiction over large class action lawsuits to address perceived abuses in state courts.
  • B. CAFA
    CAFA (Central Asian Football Association) is the regional governing body for football in Central Asia under the Asian Football Confederation (AFC).
  • C. CAFAM
    CAFAM is a Los Angeles museum dedicated to contemporary craft, art, and design, showcasing innovative works in ceramics, fiber, wood, and other materials.
  • D. CAFF
    CAFF is an Arctic Council working group focused on the conservation and sustainable use of Arctic biodiversity, ecosystems, and related natural resources.
  • E. UCCA
    UCCA is a New York State statute that governs the organization, jurisdiction, and procedures of the state's city courts.
  • 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_69d8d395dba0819087568404508590cb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e58d7ecca881909d6c262837b621b3 completed April 20, 2026, 2:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053d3e4f048190b72ec4ed1dec6c55 completed May 14, 2026, 3:10 a.m.
NEDg Description generation batch_6a053f3c45308190a87170c5d54ff3cd completed May 14, 2026, 3:19 a.m.
NED2 Entity disambiguation (via description) batch_6a053fd358a08190a1cd97c02f0e814e completed May 14, 2026, 3:21 a.m.
Created at: April 10, 2026, 11:52 a.m.