Triple

T3337454
Position Surface form Disambiguated ID Type / Status
Subject Tsonga E70172 entity
Predicate ISO639-2Code P208 FINISHED
Object tso
tso is the ISO 639-2 three-letter code for the Tsonga language, a Bantu language spoken primarily in southern Africa.
 E349726 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: tso | Statement: [Tsonga, ISO639-2Code, tso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: tso
Context triple: [Tsonga, ISO639-2Code, tso]
  • A. TSO
    TSO (The Stationery Office) is a major UK publishing and information services company known for producing and distributing official government and public sector documents.
  • B. TOS
    TOS is an abbreviation that most commonly refers to "Terms of Service," the rules and conditions governing the use of a service or platform.
  • C. TTO
    TTO is a DARPA office focused on developing and demonstrating high-risk, high-payoff advanced military technologies and systems.
  • D. TTO
    TTO is the FIFA country code representing the Trinidad and Tobago national football team in international competitions.
  • E. TSE
    TSE is the primary stock exchange in Japan and one of the largest securities markets in the world, located in Tokyo.
  • 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: tso
Triple: [Tsonga, ISO639-2Code, tso]
Generated description
tso is the ISO 639-2 three-letter code for the Tsonga language, a Bantu language spoken primarily in southern Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: tso
Target entity description: tso is the ISO 639-2 three-letter code for the Tsonga language, a Bantu language spoken primarily in southern Africa.
  • A. TSO
    TSO (The Stationery Office) is a major UK publishing and information services company known for producing and distributing official government and public sector documents.
  • B. TOS
    TOS is an abbreviation that most commonly refers to "Terms of Service," the rules and conditions governing the use of a service or platform.
  • C. TTO
    TTO is a DARPA office focused on developing and demonstrating high-risk, high-payoff advanced military technologies and systems.
  • D. TTO
    TTO is the FIFA country code representing the Trinidad and Tobago national football team in international competitions.
  • E. TSE
    TSE is the primary stock exchange in Japan and one of the largest securities markets in the world, located in Tokyo.
  • 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_69ad85a24f208190bcf83131bfed3521 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1bc31b4819085f01e0b5a7cbc5d completed March 8, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a8ad1a8819081d7ad2a48e2c5b9 completed March 12, 2026, 7:56 p.m.
NEDg Description generation batch_69b31c3aaba48190b203e344d71080f3 completed March 12, 2026, 8:04 p.m.
NED2 Entity disambiguation (via description) batch_69b31da28a04819096e7ced5f123592a completed March 12, 2026, 8:10 p.m.
Created at: March 8, 2026, 3:12 p.m.