Triple

T2559888
Position Surface form Disambiguated ID Type / Status
Subject Svan language E57216 entity
Predicate hasISO6393Code P8719 FINISHED
Object sva
sva is the ISO 639-3 code for the Svan language, a Kartvelian language spoken by the Svan people in the Svaneti region of northwestern Georgia.
E278113 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: sva | Statement: [Svan language, hasISO6393Code, sva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sva
Context triple: [Svan language, hasISO6393Code, sva]
  • A. SVA
    SVA is the ICAO airline designator used to identify Saudia, the flag carrier airline of Saudi Arabia, in international aviation operations.
  • B. SV
    SV is the two-letter ISO 3166-1 alpha-2 country code assigned to El Salvador.
  • C. SV
    SV is the commonly used abbreviation for the Faculty of Social Sciences at the University of Oslo, encompassing disciplines such as sociology, political science, economics, and related fields.
  • D. SVC
    SVC is scikit-learn’s implementation of a Support Vector Machine classifier used for supervised learning tasks such as binary and multiclass classification.
  • E. SVR
    SVR is Russia’s primary foreign intelligence service, which succeeded the Soviet-era KGB’s external intelligence functions after the USSR’s dissolution.
  • 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: sva
Triple: [Svan language, hasISO6393Code, sva]
Generated description
sva is the ISO 639-3 code for the Svan language, a Kartvelian language spoken by the Svan people in the Svaneti region of northwestern Georgia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: sva
Target entity description: sva is the ISO 639-3 code for the Svan language, a Kartvelian language spoken by the Svan people in the Svaneti region of northwestern Georgia.
  • A. SVA
    SVA is the ICAO airline designator used to identify Saudia, the flag carrier airline of Saudi Arabia, in international aviation operations.
  • B. SV
    SV is the two-letter ISO 3166-1 alpha-2 country code assigned to El Salvador.
  • C. SV
    SV is the commonly used abbreviation for the Faculty of Social Sciences at the University of Oslo, encompassing disciplines such as sociology, political science, economics, and related fields.
  • D. SVC
    SVC is scikit-learn’s implementation of a Support Vector Machine classifier used for supervised learning tasks such as binary and multiclass classification.
  • E. SVR
    SVR is Russia’s primary foreign intelligence service, which succeeded the Soviet-era KGB’s external intelligence functions after the USSR’s dissolution.
  • 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_69ab4a4ef9008190a0e6d4422b9418b7 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd333370c8190b1d64ec99e999913 completed March 7, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69af5d233dbc81909feb1127cffb027f completed March 9, 2026, 11:52 p.m.
NEDg Description generation batch_69af60e78b488190bdd01ee77ed3648b completed March 10, 2026, 12:08 a.m.
NED2 Entity disambiguation (via description) batch_69af614ad2408190955c430cb7a7e302 completed March 10, 2026, 12:09 a.m.
Created at: March 6, 2026, 9:48 p.m.