Triple

T23253363
Position Surface form Disambiguated ID Type / Status
Subject Venda region E581796 entity
Predicate contains P35 FINISHED
Object Sibasa
Sibasa is a town in South Africa’s Limpopo province, historically significant as a former administrative and cultural center of the Venda people.
 E1579083 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: Sibasa | Statement: [Venda region, contains, Sibasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sibasa
Context triple: [Venda region, contains, Sibasa]
  • A. Emgesa
    Emgesa is an energy company that operates hydroelectric power facilities in Colombia.
  • B. Mabasa
    Mabasa is a barangay (village-level administrative division) within the municipality of Argao in Cebu, Philippines.
  • C. Sibutu
    Sibutu is a small but strategically located island in the southern Philippines near the maritime border with Malaysia, known for its role in regional sea routes and its predominantly Muslim population.
  • D. Bashenga
    Bashenga is a legendary Wakandan warrior and the first Black Panther, revered as the founder of the Panther cult and an ancestor of T'Challa in Marvel Comics.
  • E. Soshanguve
    Soshanguve is a large township in the northern part of the Gauteng province of South Africa, known for its diverse population and proximity to Pretoria.
  • 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: Sibasa
Triple: [Venda region, contains, Sibasa]
Generated description
Sibasa is a town in South Africa’s Limpopo province, historically significant as a former administrative and cultural center of the Venda people.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sibasa
Target entity description: Sibasa is a town in South Africa’s Limpopo province, historically significant as a former administrative and cultural center of the Venda people.
  • A. Emgesa
    Emgesa is an energy company that operates hydroelectric power facilities in Colombia.
  • B. Mabasa
    Mabasa is a barangay (village-level administrative division) within the municipality of Argao in Cebu, Philippines.
  • C. Sibutu
    Sibutu is a small but strategically located island in the southern Philippines near the maritime border with Malaysia, known for its role in regional sea routes and its predominantly Muslim population.
  • D. Bashenga
    Bashenga is a legendary Wakandan warrior and the first Black Panther, revered as the founder of the Panther cult and an ancestor of T'Challa in Marvel Comics.
  • E. Soshanguve
    Soshanguve is a large township in the northern part of the Gauteng province of South Africa, known for its diverse population and proximity to Pretoria.
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f840dc819098e52272abefe616 completed April 29, 2026, 5:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c3f6a050c81908242087190a5a42e completed May 19, 2026, 10:46 a.m.
NEDg Description generation batch_6a0c4028b44c8190bde6e2c76b5f1587 completed May 19, 2026, 10:49 a.m.
NED2 Entity disambiguation (via description) batch_6a0c4367753c8190a4f6dbf2afd12b76 completed May 19, 2026, 11:03 a.m.
Created at: April 17, 2026, 4:11 p.m.