Triple

T5729712
Position Surface form Disambiguated ID Type / Status
Subject Norwegian Defence Research Establishment E126350 entity
Predicate shortName P43 FINISHED
Object FFI
FFI is Norway’s primary defense research institute, conducting scientific and technological research to support the country’s armed forces and security policy.
 E540490 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: FFI | Statement: [Norwegian Defence Research Establishment, shortName, FFI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FFI
Context triple: [Norwegian Defence Research Establishment, shortName, FFI]
  • A. FFI
    FFI refers to the French Forces of the Interior, the unified resistance movement that fought against German occupation and the Vichy regime in France during World War II.
  • B. FFC
    FFC is the common abbreviation for Fluminense Football Club, a traditional Brazilian sports club best known for its professional football team based in Rio de Janeiro.
  • C. FFC
    FFC is the commonly used abbreviation for Falkirk Football Club, a professional Scottish football team based in Falkirk.
  • D. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • E. FFO
    FFO is the IATA airport code for Wright-Patterson Air Force Base, a major United States Air Force installation near Dayton, Ohio.
  • 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: FFI
Triple: [Norwegian Defence Research Establishment, shortName, FFI]
Generated description
FFI is Norway’s primary defense research institute, conducting scientific and technological research to support the country’s armed forces and security policy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FFI
Target entity description: FFI is Norway’s primary defense research institute, conducting scientific and technological research to support the country’s armed forces and security policy.
  • A. FFI
    FFI refers to the French Forces of the Interior, the unified resistance movement that fought against German occupation and the Vichy regime in France during World War II.
  • B. FFC
    FFC is the common abbreviation for Fluminense Football Club, a traditional Brazilian sports club best known for its professional football team based in Rio de Janeiro.
  • C. FFC
    FFC is the commonly used abbreviation for Falkirk Football Club, a professional Scottish football team based in Falkirk.
  • D. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • E. FFO
    FFO is the IATA airport code for Wright-Patterson Air Force Base, a major United States Air Force installation near Dayton, Ohio.
  • 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_69c0082f723881908ce8bb13a0c0f8b7 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c025303860819093e51f176babed71 completed March 22, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a8cca748190b471c842fd2ce218 completed March 22, 2026, 9:09 p.m.
NEDg Description generation batch_69c05b7c3bd48190ad8303bf1bb3ec6a completed March 22, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_69c05c22c31081909a9a67d99e7c728c completed March 22, 2026, 9:16 p.m.
Created at: March 22, 2026, 3:47 p.m.