Triple

T17990076
Position Surface form Disambiguated ID Type / Status
Subject South African Special Forces Brigade E430343 entity
Predicate abbreviation P43 FINISHED
Object SASF
SASF is the abbreviation for the South African Special Forces Brigade, an elite special operations unit of the South African National Defence Force.
 E1299833 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: SASF | Statement: [South African Special Forces Brigade, abbreviation, SASF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SASF
Context triple: [South African Special Forces Brigade, abbreviation, SASF]
  • A. SFS
    SFS is the commonly used abbreviation for the San Francisco Symphony, a major American orchestra based in San Francisco, California.
  • B. SFS
    SFS is a common abbreviation for Allianz Stadium, a major sports and entertainment venue in Sydney, Australia.
  • C. SFS
    SFS is the common abbreviation for the Sioux Falls Stampede, a junior ice hockey team in the United States Hockey League based in Sioux Falls, South Dakota.
  • D. SFS
    SFS is a renowned Georgetown University school specializing in international affairs, diplomacy, and global policy education.
  • E. SFS
    SFS is a spatial feature standard that defines how geographic features and their properties are modeled and accessed in geospatial information systems.
  • 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: SASF
Triple: [South African Special Forces Brigade, abbreviation, SASF]
Generated description
SASF is the abbreviation for the South African Special Forces Brigade, an elite special operations unit of the South African National Defence Force.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SASF
Target entity description: SASF is the abbreviation for the South African Special Forces Brigade, an elite special operations unit of the South African National Defence Force.
  • A. SFS
    SFS is the commonly used abbreviation for the San Francisco Symphony, a major American orchestra based in San Francisco, California.
  • B. SFS
    SFS is a common abbreviation for Allianz Stadium, a major sports and entertainment venue in Sydney, Australia.
  • C. SFS
    SFS is the common abbreviation for the Sioux Falls Stampede, a junior ice hockey team in the United States Hockey League based in Sioux Falls, South Dakota.
  • D. SFS
    SFS is a renowned Georgetown University school specializing in international affairs, diplomacy, and global policy education.
  • E. SFS
    SFS is the abbreviation for the Senior Foreign Service, the elite cadre of senior-ranking career diplomats in the United States Foreign Service.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29f127c81908b0c4cb3787e002c completed April 19, 2026, 10:46 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0337acabd481909deced9a61d84ed3 completed May 12, 2026, 2:22 p.m.
NEDg Description generation batch_6a0338cd02808190b650f59fc16bab0d completed May 12, 2026, 2:27 p.m.
NED2 Entity disambiguation (via description) batch_6a033cb498248190a3805cd356832cd0 completed May 12, 2026, 2:44 p.m.
Created at: April 10, 2026, 10:23 a.m.