Triple

T5481103
Position Surface form Disambiguated ID Type / Status
Subject Security Edge Protection Proxy E123467 entity
Predicate abbreviation P43 FINISHED
Object SEPP
SEPP (Security Edge Protection Proxy) is a 5G network security function that protects signaling traffic at the network edge, enabling secure and trusted interconnection between different operators’ networks.
 E523102 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: SEPP | Statement: [Security Edge Protection Proxy, abbreviation, SEPP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SEPP
Context triple: [Security Edge Protection Proxy, abbreviation, SEPP]
  • A. SEP
    SEP is the Mexican federal government department responsible for overseeing and regulating the national education system.
  • B. SEP
    SEP is the commonly used abbreviation for Sociedade Esportiva Palmeiras, one of Brazil’s most successful and popular football clubs.
  • C. SEGU
    SEGU is the ICAO airport code for José Joaquín de Olmedo International Airport, the main air gateway serving Guayaquil, Ecuador.
  • D. SEB
    SEB is the IATA airport code for Sabha Airport, which serves the city of Sabha in southwestern Libya.
  • E. SEBL
    SEBL was the stock ticker symbol for Siebel Systems, a prominent customer relationship management (CRM) software company later acquired by Oracle.
  • 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: SEPP
Triple: [Security Edge Protection Proxy, abbreviation, SEPP]
Generated description
SEPP (Security Edge Protection Proxy) is a 5G network security function that protects signaling traffic at the network edge, enabling secure and trusted interconnection between different operators’ networks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SEPP
Target entity description: SEPP (Security Edge Protection Proxy) is a 5G network security function that protects signaling traffic at the network edge, enabling secure and trusted interconnection between different operators’ networks.
  • A. SEP
    SEP is the Mexican federal government department responsible for overseeing and regulating the national education system.
  • B. SEP
    SEP is the commonly used abbreviation for Sociedade Esportiva Palmeiras, one of Brazil’s most successful and popular football clubs.
  • C. SEGU
    SEGU is the ICAO airport code for José Joaquín de Olmedo International Airport, the main air gateway serving Guayaquil, Ecuador.
  • D. SEB
    SEB is the IATA airport code for Sabha Airport, which serves the city of Sabha in southwestern Libya.
  • E. SEBL
    SEBL was the stock ticker symbol for Siebel Systems, a prominent customer relationship management (CRM) software company later acquired by Oracle.
  • 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_69bd4648883481909e9775d43300c5fa completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd924a2eb08190b759b23a6eab5e0a completed March 20, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf48a2880c8190ad76cf8c3862aede completed March 22, 2026, 1:40 a.m.
NEDg Description generation batch_69bf4a95375881909ba730ad108eee8b completed March 22, 2026, 1:49 a.m.
NED2 Entity disambiguation (via description) batch_69bf4afb47a88190a66de6b6c7d5c241 completed March 22, 2026, 1:50 a.m.
Created at: March 20, 2026, 2:09 p.m.