Triple

T20677607
Position Surface form Disambiguated ID Type / Status
Subject Southern University System E508200 entity
Predicate hasAbbreviation P43 FINISHED
Object SUS
SUS is the abbreviation for the Southern University System, a public historically Black university system based in Louisiana.
 E1443936 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: SUS | Statement: [Southern University System, hasAbbreviation, SUS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SUS
Context triple: [Southern University System, hasAbbreviation, SUS]
  • A. SUS
    SUS is the commonly used abbreviation for the State University System of Florida, the network of public universities in the state of Florida.
  • B. SUS
    SUS is a standardized specification that defines the requirements for a compliant UNIX operating system, ensuring compatibility and interoperability across different UNIX implementations.
  • C. SUS
    SUS is the IATA airport code for Spirit of St. Louis Airport, a public airport serving the St. Louis metropolitan area in Missouri, United States.
  • D. SUS
    SUS is a major Swedish university hospital and medical research center located in the Skåne region.
  • E. SUSP
    SUSP is a protocol used in ISO 9660 file systems to support extended file system features and metadata beyond the standard specification.
  • 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: SUS
Triple: [Southern University System, hasAbbreviation, SUS]
Generated description
SUS is the abbreviation for the Southern University System, a public historically Black university system based in Louisiana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SUS
Target entity description: SUS is the abbreviation for the Southern University System, a public historically Black university system based in Louisiana.
  • A. SUS
    SUS is the commonly used abbreviation for the State University System of Florida, the network of public universities in the state of Florida.
  • B. SUS
    SUS is a standardized specification that defines the requirements for a compliant UNIX operating system, ensuring compatibility and interoperability across different UNIX implementations.
  • C. SUS
    SUS is the IATA airport code for Spirit of St. Louis Airport, a public airport serving the St. Louis metropolitan area in Missouri, United States.
  • D. SUS
    SUS is a major Swedish university hospital and medical research center located in the Skåne region.
  • E. SUSP
    SUSP is a protocol used in ISO 9660 file systems to support extended file system features and metadata beyond the standard specification.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6bea24f288190928f828e5f567257 completed April 21, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08cd6aa744819098c785d7195cdd2e completed May 16, 2026, 8:02 p.m.
NEDg Description generation batch_6a08d176c3408190ab1d630fd8da2fc2 completed May 16, 2026, 8:20 p.m.
NED2 Entity disambiguation (via description) batch_6a08d206e6a081909f76b190c8dbc55d completed May 16, 2026, 8:22 p.m.
Created at: April 16, 2026, 11:44 a.m.