Triple

T8080173
Position Surface form Disambiguated ID Type / Status
Subject Sekopa dialect E188593 entity
Predicate hasAlternativeName P39 FINISHED
Object Sekopa
Sekopa is a Bantu language variety spoken in parts of southern Africa, recognized as a dialect within the broader Sotho-Tswana language group.
E710530 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: Sekopa | Statement: [Sekopa dialect, hasAlternativeName, Sekopa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sekopa
Context triple: [Sekopa dialect, hasAlternativeName, Sekopa]
  • A. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • B. Pichichi
    Pichichi was a famed early 20th-century Spanish footballer and prolific Athletic Bilbao forward whose legacy lives on through La Liga’s top-scorer award bearing his nickname.
  • C. Totsakan
    Totsakan is the ten-headed demon king of Lanka in the Thai epic Ramakien, serving as its central villain and a key figure in Thai classical literature and performance.
  • D. Bola
    Bola is the given name of Bola Tinubu, a prominent Nigerian politician and current president of Nigeria.
  • E. Shama
    Shama is a coastal town in Ghana known historically as a fishing community and trading post along the Gulf of Guinea.
  • 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: Sekopa
Triple: [Sekopa dialect, hasAlternativeName, Sekopa]
Generated description
Sekopa is a Bantu language variety spoken in parts of southern Africa, recognized as a dialect within the broader Sotho-Tswana language group.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sekopa
Target entity description: Sekopa is a Bantu language variety spoken in parts of southern Africa, recognized as a dialect within the broader Sotho-Tswana language group.
  • A. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • B. Pichichi
    Pichichi was a famed early 20th-century Spanish footballer and prolific Athletic Bilbao forward whose legacy lives on through La Liga’s top-scorer award bearing his nickname.
  • C. Totsakan
    Totsakan is the ten-headed demon king of Lanka in the Thai epic Ramakien, serving as its central villain and a key figure in Thai classical literature and performance.
  • D. Bola
    Bola is the given name of Bola Tinubu, a prominent Nigerian politician and current president of Nigeria.
  • E. Shama
    Shama is a coastal town in Ghana known historically as a fishing community and trading post along the Gulf of Guinea.
  • 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_69ca82b662e88190b9323daab8c28a21 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb40a504d48190ace96e814d99b182 completed March 31, 2026, 3:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63f79ac08190af49e77bee67921d completed April 1, 2026, 12:16 a.m.
NEDg Description generation batch_69cc651d340c819089306bac7110f57a completed April 1, 2026, 12:21 a.m.
NED2 Entity disambiguation (via description) batch_69cc666ecc04819092ee4cc035dde627 completed April 1, 2026, 12:27 a.m.
Created at: March 30, 2026, 5:28 p.m.