Triple

T16397584
Position Surface form Disambiguated ID Type / Status
Subject Gold Reef City E398222 entity
Predicate operator P179 FINISHED
Object Tsogo Sun
Tsogo Sun is a major South African hospitality and gaming group that owns and operates hotels, casinos, and entertainment complexes across the country.
 E1209613 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: Tsogo Sun | Statement: [Gold Reef City, operator, Tsogo Sun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tsogo Sun
Context triple: [Gold Reef City, operator, Tsogo Sun]
  • A. Tsogo
    Tsogo is a Bantu language of Central Africa, spoken primarily in Gabon and closely related to Njebi.
  • B. Motele
    Motele is a small town in present-day Belarus, historically part of the Pale of Settlement and home to a notable Jewish community.
  • C. Eshowe
    Eshowe is a historic town in South Africa’s KwaZulu-Natal province, notable as a center of Zulu history and colonial-era conflict.
  • D. Shingwedzi Rest Camp
    Shingwedzi Rest Camp is a popular riverside safari camp in the northern region of South Africa’s Kruger National Park, known for its rustic atmosphere and excellent wildlife viewing opportunities.
  • E. Zinzana
    Zinzana is a 2015 Emirati thriller film directed by Majid Al Ansari, known for its tense, single-location story about a man trapped in a police station with a dangerous stranger.
  • 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: Tsogo Sun
Triple: [Gold Reef City, operator, Tsogo Sun]
Generated description
Tsogo Sun is a major South African hospitality and gaming group that owns and operates hotels, casinos, and entertainment complexes across the country.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tsogo Sun
Target entity description: Tsogo Sun is a major South African hospitality and gaming group that owns and operates hotels, casinos, and entertainment complexes across the country.
  • A. Tsogo
    Tsogo is a Bantu language of Central Africa, spoken primarily in Gabon and closely related to Njebi.
  • B. Motele
    Motele is a small town in present-day Belarus, historically part of the Pale of Settlement and home to a notable Jewish community.
  • C. Eshowe
    Eshowe is a historic town in South Africa’s KwaZulu-Natal province, notable as a center of Zulu history and colonial-era conflict.
  • D. Shingwedzi Rest Camp
    Shingwedzi Rest Camp is a popular riverside safari camp in the northern region of South Africa’s Kruger National Park, known for its rustic atmosphere and excellent wildlife viewing opportunities.
  • E. Zinzana
    Zinzana is a 2015 Emirati thriller film directed by Majid Al Ansari, known for its tense, single-location story about a man trapped in a police station with a dangerous stranger.
  • 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e327cc5c9c8190ba1a70f9e430cefb completed April 18, 2026, 6:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00357838a88190be88c51f454be6eb completed May 10, 2026, 7:36 a.m.
NEDg Description generation batch_6a0035ea77dc8190bda37dac2710d0e3 completed May 10, 2026, 7:38 a.m.
NED2 Entity disambiguation (via description) batch_6a0036e53f2c81908f04a5e51870040c completed May 10, 2026, 7:42 a.m.
Created at: April 10, 2026, 5:09 a.m.