Triple

T16051326
Position Surface form Disambiguated ID Type / Status
Subject Guangzhou Academy of Fine Arts E389358 entity
Predicate shortName P43 FINISHED
Object GAFA
GAFA is an art and design university in Guangzhou, China, known for its programs in fine arts, design, and related creative disciplines.
E1191364 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: GAFA | Statement: [Guangzhou Academy of Fine Arts, shortName, GAFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GAFA
Context triple: [Guangzhou Academy of Fine Arts, shortName, GAFA]
  • A. GFA
    GFA is the governing body responsible for organizing and overseeing football activities and competitions in Ghana.
  • B. GFA
    GFA is the ICAO airline designator used for Gulf Air, the national carrier of Bahrain.
  • C. GIZ
    GIZ is a German government-owned development agency that provides international cooperation services for sustainable development and international education.
  • D. GIZ
    GIZ is the IATA airport code for Jazan Regional Airport in Jazan, Saudi Arabia.
  • E. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • 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: GAFA
Triple: [Guangzhou Academy of Fine Arts, shortName, GAFA]
Generated description
GAFA is an art and design university in Guangzhou, China, known for its programs in fine arts, design, and related creative disciplines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: GAFA
Target entity description: GAFA is an art and design university in Guangzhou, China, known for its programs in fine arts, design, and related creative disciplines.
  • A. GFA
    GFA is the governing body responsible for organizing and overseeing football activities and competitions in Ghana.
  • B. GFA
    GFA is the ICAO airline designator used for Gulf Air, the national carrier of Bahrain.
  • C. GIZ
    GIZ is a German government-owned development agency that provides international cooperation services for sustainable development and international education.
  • D. GIZ
    GIZ is the IATA airport code for Jazan Regional Airport in Jazan, Saudi Arabia.
  • E. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18361c31481908b253e8b814ec9f6 completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbe095908190ba10399ad6f3b5f8 completed May 10, 2026, 1:14 a.m.
NEDg Description generation batch_69ffdcdb551c8190b367407b749314e8 completed May 10, 2026, 1:18 a.m.
NED2 Entity disambiguation (via description) batch_69ffddbfaf088190a644e7898f995c1d completed May 10, 2026, 1:22 a.m.
Created at: April 10, 2026, 4:56 a.m.