Triple

T4122895
Position Surface form Disambiguated ID Type / Status
Subject Saho E92654 entity
Predicate ISO639-3Code P208 FINISHED
Object ssy
ssy is the ISO 639-3 language code for Saho, a Cushitic language spoken primarily in Eritrea and Ethiopia.
 E416296 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: ssy | Statement: [Saho, ISO639-3Code, ssy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ssy
Context triple: [Saho, ISO639-3Code, ssy]
  • A. .ss
    .ss is the country code top-level domain (ccTLD) assigned to South Sudan for use in its internet addresses.
  • B. YSSY
    YSSY is the ICAO airport code for Sydney Kingsford Smith Airport, the primary international airport serving Sydney, Australia.
  • C. SS
    SS is the UK postcode area covering Southend-on-Sea and surrounding parts of Essex in eastern England.
  • D. SS
    The SS was a paramilitary organization of Nazi Germany that became one of the principal instruments of terror, repression, and mass murder, including the systematic genocide of Jews and other targeted groups during World War II.
  • E. SS
    SS is the IATA airline designator used to identify Corsair International flights in global aviation 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: ssy
Triple: [Saho, ISO639-3Code, ssy]
Generated description
ssy is the ISO 639-3 language code for Saho, a Cushitic language spoken primarily in Eritrea and Ethiopia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ssy
Target entity description: ssy is the ISO 639-3 language code for Saho, a Cushitic language spoken primarily in Eritrea and Ethiopia.
  • A. .ss
    .ss is the country code top-level domain (ccTLD) assigned to South Sudan for use in its internet addresses.
  • B. YSSY
    YSSY is the ICAO airport code for Sydney Kingsford Smith Airport, the primary international airport serving Sydney, Australia.
  • C. SS
    SS is the UK postcode area covering Southend-on-Sea and surrounding parts of Essex in eastern England.
  • D. SS
    The SS was a paramilitary organization of Nazi Germany that became one of the principal instruments of terror, repression, and mass murder, including the systematic genocide of Jews and other targeted groups during World War II.
  • E. SS
    SS is the IATA airline designator used to identify Corsair International flights in global aviation systems.
  • 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_69aed9685f70819086932777aec8d959 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69af020728a08190a50a16b40690cbce completed March 9, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576b405548190affdd8bb108995b1 completed March 14, 2026, 2:54 p.m.
NEDg Description generation batch_69b577653214819093396a8601e52245 completed March 14, 2026, 2:57 p.m.
NED2 Entity disambiguation (via description) batch_69b57b90cb308190ba102f999795829c completed March 14, 2026, 3:15 p.m.
Created at: March 9, 2026, 3:41 p.m.