Triple

T10224712
Position Surface form Disambiguated ID Type / Status
Subject Mandela Challenge Plate E243175 entity
Predicate alsoKnownAs P39 FINISHED
Object Mandela Plate
The Mandela Plate is a South African horse racing trophy event named in honor of Nelson Mandela, attracting top thoroughbreds to compete annually.
E850578 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: Mandela Plate | Statement: [Mandela Challenge Plate, alsoKnownAs, Mandela Plate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandela Plate
Context triple: [Mandela Challenge Plate, alsoKnownAs, Mandela Plate]
  • A. Mengistu
    Mengistu is a male given name of Ethiopian origin, notably borne by several prominent Ethiopian political and military figures.
  • B. Wazwan
    Wazwan is a lavish multi-course feast from Kashmir, renowned for its rich meat-based dishes and central role in weddings and special celebrations.
  • C. Tsévié
    Tsévié is a town in southern Togo that serves as an important regional center for trade and agriculture.
  • D. Balado
    Balado is a small settlement in Kinross-shire, Scotland, best known for its former NATO communications base and as the long-time site of the T in the Park music festival.
  • E. Manda
    Manda is a lesser-known Dravidian language spoken by tribal communities in parts of eastern India, particularly in Odisha.
  • 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: Mandela Plate
Triple: [Mandela Challenge Plate, alsoKnownAs, Mandela Plate]
Generated description
The Mandela Plate is a South African horse racing trophy event named in honor of Nelson Mandela, attracting top thoroughbreds to compete annually.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mandela Plate
Target entity description: The Mandela Plate is a South African horse racing trophy event named in honor of Nelson Mandela, attracting top thoroughbreds to compete annually.
  • A. Mengistu
    Mengistu is a male given name of Ethiopian origin, notably borne by several prominent Ethiopian political and military figures.
  • B. Wazwan
    Wazwan is a lavish multi-course feast from Kashmir, renowned for its rich meat-based dishes and central role in weddings and special celebrations.
  • C. Tsévié
    Tsévié is a town in southern Togo that serves as an important regional center for trade and agriculture.
  • D. Balado
    Balado is a small settlement in Kinross-shire, Scotland, best known for its former NATO communications base and as the long-time site of the T in the Park music festival.
  • E. Manda
    Manda is a lesser-known Dravidian language spoken by tribal communities in parts of eastern India, particularly in Odisha.
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d1f860048190bb20f7d3bf87f347 completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6a8457e9c819085f222bb002be892 completed April 8, 2026, 7:11 p.m.
NEDg Description generation batch_69d6d00220ec81909d189e64eda2a28f completed April 8, 2026, 10 p.m.
NED2 Entity disambiguation (via description) batch_69d6df44ad5481909100b596d2bf3b07 completed April 8, 2026, 11:05 p.m.
Created at: April 6, 2026, 11:16 a.m.