Triple

T22904592
Position Surface form Disambiguated ID Type / Status
Subject Fryske Akademy E568410 entity
Predicate shortName P43 FINISHED
Object FA
FA is the abbreviation for the Fryske Akademy, a research institute in the Netherlands dedicated to Frisian language, culture, history, and society.
 E1560458 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: FA | Statement: [Fryske Akademy, shortName, FA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FA
Context triple: [Fryske Akademy, shortName, FA]
  • A. FA
    FA is a Chilean left-wing political coalition known for uniting various progressive parties and movements to challenge the country’s traditional political blocs.
  • B. FA
    FA is the governing body of association football in England, responsible for overseeing the national teams, competitions, and the rules of the game within the country.
  • C. FA
    FA is the IATA airline designator assigned to FlySafair, a South African low-cost carrier.
  • D. Fa
    Fa was the personal name of King Wu of Zhou, the founding monarch of China’s Zhou dynasty who overthrew the Shang.
  • E. F
    F is the New York Stock Exchange ticker symbol for Ford Motor Company, the American multinational automaker known for mass-producing automobiles and pioneering assembly line manufacturing.
  • 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: FA
Triple: [Fryske Akademy, shortName, FA]
Generated description
FA is the abbreviation for the Fryske Akademy, a research institute in the Netherlands dedicated to Frisian language, culture, history, and society.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FA
Target entity description: FA is the abbreviation for the Fryske Akademy, a research institute in the Netherlands dedicated to Frisian language, culture, history, and society.
  • A. FA
    FA is a Chilean left-wing political coalition known for uniting various progressive parties and movements to challenge the country’s traditional political blocs.
  • B. FA
    FA is the governing body of association football in England, responsible for overseeing the national teams, competitions, and the rules of the game within the country.
  • C. FA
    FA is the IATA airline designator assigned to FlySafair, a South African low-cost carrier.
  • D. Fa
    Fa was the personal name of King Wu of Zhou, the founding monarch of China’s Zhou dynasty who overthrew the Shang.
  • E. F
    F is a tram line in the Strasbourg tramway network in France, serving various districts of the city and its suburbs.
  • 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_69e2458cd9e48190943ad2e34485d939 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1801895f48190bb8d49a41feac7ef completed April 29, 2026, 3:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bb9cbbdf481909d628c86abc8f515 completed May 19, 2026, 1:15 a.m.
NEDg Description generation batch_6a0bbb6ca76c8190bde7e1eacb121d23 completed May 19, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_6a0bbc15b59c8190b918d551b1fb3230 completed May 19, 2026, 1:25 a.m.
Created at: April 17, 2026, 3:41 p.m.