Triple

T14864813
Position Surface form Disambiguated ID Type / Status
Subject National Széchényi Library E349589 entity
Predicate shortName P43 FINISHED
Object OSZK
OSZK is the commonly used abbreviation for Hungary’s National Széchényi Library, the country’s primary national library and major cultural institution.
 E1123490 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: OSZK | Statement: [National Széchényi Library, shortName, OSZK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: OSZK
Context triple: [National Széchényi Library, shortName, OSZK]
  • A. OZD
    OZD is the official abbreviation for the Netherlands Submarine Service, the branch of the Royal Netherlands Navy responsible for operating the country's submarine fleet.
  • B. OZG
    OZG is the IATA airport code for Zagora Airport, a public airport serving the Zagora region in Morocco.
  • C. OZN
    OZN was a Polish political organization associated with the interwar Sanation regime, supporting its authoritarian and nationalist policies.
  • D. OZP
    OZP is the IATA airport code for Morón Air Base, a military airfield located near Seville in southern Spain.
  • E. OSO
    OSO is the commonly used abbreviation for the Office of SIGINT Operations, a signals intelligence unit within the U.S. National Security Agency.
  • 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: OSZK
Triple: [National Széchényi Library, shortName, OSZK]
Generated description
OSZK is the commonly used abbreviation for Hungary’s National Széchényi Library, the country’s primary national library and major cultural institution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: OSZK
Target entity description: OSZK is the commonly used abbreviation for Hungary’s National Széchényi Library, the country’s primary national library and major cultural institution.
  • A. OZD
    OZD is the official abbreviation for the Netherlands Submarine Service, the branch of the Royal Netherlands Navy responsible for operating the country's submarine fleet.
  • B. OZG
    OZG is the IATA airport code for Zagora Airport, a public airport serving the Zagora region in Morocco.
  • C. OZN
    OZN was a Polish political organization associated with the interwar Sanation regime, supporting its authoritarian and nationalist policies.
  • D. OZP
    OZP is the IATA airport code for Morón Air Base, a military airfield located near Seville in southern Spain.
  • E. OSO
    OSO is the commonly used abbreviation for the Office of SIGINT Operations, a signals intelligence unit within the U.S. National Security Agency.
  • 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_69d822ed7e1881909b90fca143ad7e34 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded574d0ec8190a6afed672ba6c2f9 completed April 15, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe650e8aec8190acd4a9cb9cad2039 completed May 8, 2026, 10:34 p.m.
NEDg Description generation batch_69fe65ac6a5c81908621dc17edc6b04f completed May 8, 2026, 10:37 p.m.
NED2 Entity disambiguation (via description) batch_69fe6697fe3881908aae42abe56d86f8 completed May 8, 2026, 10:41 p.m.
Created at: April 10, 2026, 1:54 a.m.