Triple

T8587503
Position Surface form Disambiguated ID Type / Status
Subject Finnish Security Intelligence Service E203342 entity
Predicate shortName P43 FINISHED
Object SUPO
SUPO is Finland’s national security and intelligence agency responsible for counterintelligence, counterterrorism, and protecting the country’s internal security.
 E746182 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: SUPO | Statement: [Finnish Security Intelligence Service, shortName, SUPO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SUPO
Context triple: [Finnish Security Intelligence Service, shortName, SUPO]
  • A. SOU
    SOU is the three-letter IATA airport code for Southampton Airport in Hampshire, England.
  • B. SOU
    SOU is the three-letter National Rail station code for Southampton Central railway station in Hampshire, England.
  • C. Su
    Su is a skilled and deadly martial artist portrayed by Jet Li in the action film "Cradle 2 the Grave."
  • D. Su
    Su is the given name of Su Rogers, a British architect and academic known for her contributions to modern architecture and design education.
  • E. Su
    Su is a Chinese surname borne by many notable historical and contemporary figures, including the Song dynasty poet and statesman Su Shi.
  • 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: SUPO
Triple: [Finnish Security Intelligence Service, shortName, SUPO]
Generated description
SUPO is Finland’s national security and intelligence agency responsible for counterintelligence, counterterrorism, and protecting the country’s internal security.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SUPO
Target entity description: SUPO is Finland’s national security and intelligence agency responsible for counterintelligence, counterterrorism, and protecting the country’s internal security.
  • A. SOU
    SOU is the three-letter National Rail station code for Southampton Central railway station in Hampshire, England.
  • B. SOU
    SOU is the three-letter IATA airport code for Southampton Airport in Hampshire, England.
  • C. Su
    Su is a skilled and deadly martial artist portrayed by Jet Li in the action film "Cradle 2 the Grave."
  • D. Su
    Su is the given name of Su Rogers, a British architect and academic known for her contributions to modern architecture and design education.
  • E. Su
    Su is a Chinese surname borne by many notable historical and contemporary figures, including the Song dynasty poet and statesman Su Shi.
  • 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_69ca8329bb7c8190a63c643730839103 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc457dc76481908ec5ee31ad72e887 completed March 31, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea8a51db0819097ec0f70bee31539 completed April 2, 2026, 5:34 p.m.
NEDg Description generation batch_69cea996a5c48190a12ffe8e282d2d9c completed April 2, 2026, 5:38 p.m.
NED2 Entity disambiguation (via description) batch_69ceadb2d52c8190aada1d797753663e completed April 2, 2026, 5:56 p.m.
Created at: March 30, 2026, 6:23 p.m.