Triple

T3577582
Position Surface form Disambiguated ID Type / Status
Subject Armed Forces Security Agency E75724 entity
Predicate alsoKnownAs P39 FINISHED
Object AFSA
AFSA was a U.S. military signals intelligence and cryptologic organization that served as a predecessor to the National Security Agency (NSA).
 E369026 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: AFSA | Statement: [Armed Forces Security Agency, alsoKnownAs, AFSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AFSA
Context triple: [Armed Forces Security Agency, alsoKnownAs, AFSA]
  • A. AFSJ
    AFSJ is the European Union’s policy framework that governs cooperation on justice, security, border control, and fundamental rights across member states.
  • B. AFESD
    AFESD is a regional Arab financial institution that provides development financing and support to promote economic and social progress in Arab countries.
  • C. FSA
    FSA is the abbreviation for the former U.S. Federal Security Agency, a government body that once oversaw various federal social and public health programs.
  • D. AFCA
    AFCA is a U.S. federal law focused on the protection and restoration of migratory fish species that move between freshwater and saltwater environments.
  • E. USAFAS
    USAFAS is the United States Army’s primary training and doctrine institution for field artillery officers and soldiers.
  • 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: AFSA
Triple: [Armed Forces Security Agency, alsoKnownAs, AFSA]
Generated description
AFSA was a U.S. military signals intelligence and cryptologic organization that served as a predecessor to the National Security Agency (NSA).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AFSA
Target entity description: AFSA was a U.S. military signals intelligence and cryptologic organization that served as a predecessor to the National Security Agency (NSA).
  • A. AFSJ
    AFSJ is the European Union’s policy framework that governs cooperation on justice, security, border control, and fundamental rights across member states.
  • B. AFESD
    AFESD is a regional Arab financial institution that provides development financing and support to promote economic and social progress in Arab countries.
  • C. FSA
    FSA is the abbreviation for the former U.S. Federal Security Agency, a government body that once oversaw various federal social and public health programs.
  • D. AFCA
    AFCA is a U.S. federal law focused on the protection and restoration of migratory fish species that move between freshwater and saltwater environments.
  • E. USAFAS
    USAFAS is the United States Army’s primary training and doctrine institution for field artillery officers and soldiers.
  • 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_69ad85d5e3008190bdfe0bacdd1f5a1b completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0dd3e048190a0c6666e13ead9cd completed March 8, 2026, 6:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bbc3d4e88190b18ed318c55594cc completed March 13, 2026, 7:24 a.m.
NEDg Description generation batch_69b3bd01ba7881909a0987b7d5dad4c2 completed March 13, 2026, 7:30 a.m.
NED2 Entity disambiguation (via description) batch_69b3f5b6e66c81908700d5f3df0a864d completed March 13, 2026, 11:32 a.m.
Created at: March 8, 2026, 3:21 p.m.