Triple

T22908175
Position Surface form Disambiguated ID Type / Status
Subject Gauteng Department of Education E568507 entity
Predicate abbreviation P43 FINISHED
Object GDE
GDE is the provincial government department responsible for overseeing and managing public education in South Africa’s Gauteng province.
 E1560552 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: GDE | Statement: [Gauteng Department of Education, abbreviation, GDE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GDE
Context triple: [Gauteng Department of Education, abbreviation, GDE]
  • A. GDEcD
    GDEcD is the U.S. state of Georgia’s lead agency for promoting economic development, including business recruitment, trade, tourism, and film and entertainment industries.
  • B. DGE
    DGE is the London Stock Exchange ticker symbol for Diageo, a major global producer of alcoholic beverages including brands like Johnnie Walker and Guinness.
  • C. DGE
    DGE is the IATA airport code for Mudgee Airport in New South Wales, Australia.
  • D. GDS
    GDS (the Government Digital Service) is a unit of the UK government responsible for transforming public services through digital technology and user‑centred design.
  • E. GDA
    GDA is a Polish vehicle registration code assigned to cars registered in the Pomeranian Voivodeship, specifically associated with the Gdańsk area.
  • 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: GDE
Triple: [Gauteng Department of Education, abbreviation, GDE]
Generated description
GDE is the provincial government department responsible for overseeing and managing public education in South Africa’s Gauteng province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GDE
Target entity description: GDE is the provincial government department responsible for overseeing and managing public education in South Africa’s Gauteng province.
  • A. GDEcD
    GDEcD is the U.S. state of Georgia’s lead agency for promoting economic development, including business recruitment, trade, tourism, and film and entertainment industries.
  • B. DGE
    DGE is the London Stock Exchange ticker symbol for Diageo, a major global producer of alcoholic beverages including brands like Johnnie Walker and Guinness.
  • C. DGE
    DGE is the IATA airport code for Mudgee Airport in New South Wales, Australia.
  • D. GDS
    GDS (the Government Digital Service) is a unit of the UK government responsible for transforming public services through digital technology and user‑centred design.
  • E. GDA
    GDA is a Polish vehicle registration code assigned to cars registered in the Pomeranian Voivodeship, specifically associated with the Gdańsk area.
  • 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_69f18071b9ec81908922d5f046f7930a completed April 29, 2026, 3:52 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bb9cfe238819094a5802343d0feec completed May 19, 2026, 1:16 a.m.
NEDg Description generation batch_6a0bbb4c32a4819086a4bfdf25476d78 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, 3:42 p.m.