Triple

T428291
Position Surface form Disambiguated ID Type / Status
Subject Western Cape E9657 entity
Predicate contains P35 FINISHED
Object Hermanus
Hermanus is a coastal town in South Africa renowned for its land-based whale watching and scenic seaside landscapes.
E65221 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: Hermanus | Statement: [Western Cape, contains, Hermanus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hermanus
Context triple: [Western Cape, contains, Hermanus]
  • A. Mossel Bay
    Mossel Bay is a coastal town and popular tourist destination on South Africa’s Garden Route, known for its beaches, mild climate, and maritime history.
  • B. Knysna
    Knysna is a picturesque coastal town in South Africa known for its lagoon, indigenous forests, and role as a major tourist destination along the Garden Route.
  • C. Oudtshoorn
    Oudtshoorn is a South African town famed as the "ostrich capital of the world," known for its ostrich farms, Cango Caves, and semi-arid Karoo landscape.
  • D. Port Elizabeth
    Port Elizabeth is a large coastal city in South Africa known for its major seaport, automotive industry, and popular beaches along Algoa Bay.
  • E. Paarl
    Paarl is a historic town in South Africa renowned for its wine estates, scenic granite rock formations, and role in the development of the Afrikaans language.
  • 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: Hermanus
Triple: [Western Cape, contains, Hermanus]
Generated description
Hermanus is a coastal town in South Africa renowned for its land-based whale watching and scenic seaside landscapes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hermanus
Target entity description: Hermanus is a coastal town in South Africa renowned for its land-based whale watching and scenic seaside landscapes.
  • A. Mossel Bay
    Mossel Bay is a coastal town and popular tourist destination on South Africa’s Garden Route, known for its beaches, mild climate, and maritime history.
  • B. Knysna
    Knysna is a picturesque coastal town in South Africa known for its lagoon, indigenous forests, and role as a major tourist destination along the Garden Route.
  • C. Oudtshoorn
    Oudtshoorn is a South African town famed as the "ostrich capital of the world," known for its ostrich farms, Cango Caves, and semi-arid Karoo landscape.
  • D. Port Elizabeth
    Port Elizabeth is a large coastal city in South Africa known for its major seaport, automotive industry, and popular beaches along Algoa Bay.
  • E. Paarl
    Paarl is a historic town in South Africa renowned for its wine estates, scenic granite rock formations, and role in the development of the Afrikaans language.
  • 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_69a2e801e1d48190b505d1dd336b52ac completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2eeecb64c81908c5c83ef7c0181e6 completed Feb. 28, 2026, 1:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4ab1982f48190b7d7300f0ab9c637 completed March 1, 2026, 9:09 p.m.
NEDg Description generation batch_69a4ac032ef4819094b9ce7740262eda completed March 1, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_69a4ada4ca5481909bbd62b55f10f4f9 completed March 1, 2026, 9:20 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.