Triple

T3861202
Position Surface form Disambiguated ID Type / Status
Subject Glencore E90139 entity
Predicate hasSubsidiary P254 FINISHED
Object Katanga Mining Limited
Katanga Mining Limited is a mining company focused on copper and cobalt production in the Democratic Republic of Congo.
E396106 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: Katanga Mining Limited | Statement: [Glencore, hasSubsidiary, Katanga Mining Limited]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katanga Mining Limited
Context triple: [Glencore, hasSubsidiary, Katanga Mining Limited]
  • A. Mmakau Mining
    Mmakau Mining is a South African mining company known for its black female leadership and involvement in various mineral resource projects across the country.
  • B. African Rainbow Minerals
    African Rainbow Minerals is a South African diversified mining and minerals company with significant interests in platinum, iron ore, coal, copper, and other resources.
  • C. Wande Coal
    Wande Coal is a Nigerian singer and songwriter known for his influential role in modern Afrobeats and his smooth, soulful vocal style.
  • D. Codelco
    Codelco is Chile’s state-owned copper mining company and one of the world’s largest producers of copper.
  • E. Glencore
    Glencore is a multinational commodity trading and mining company that operates extensive resource extraction and processing assets worldwide.
  • 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: Katanga Mining Limited
Triple: [Glencore, hasSubsidiary, Katanga Mining Limited]
Generated description
Katanga Mining Limited is a mining company focused on copper and cobalt production in the Democratic Republic of Congo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Katanga Mining Limited
Target entity description: Katanga Mining Limited is a mining company focused on copper and cobalt production in the Democratic Republic of Congo.
  • A. Mmakau Mining
    Mmakau Mining is a South African mining company known for its black female leadership and involvement in various mineral resource projects across the country.
  • B. African Rainbow Minerals
    African Rainbow Minerals is a South African diversified mining and minerals company with significant interests in platinum, iron ore, coal, copper, and other resources.
  • C. Wande Coal
    Wande Coal is a Nigerian singer and songwriter known for his influential role in modern Afrobeats and his smooth, soulful vocal style.
  • D. Codelco
    Codelco is Chile’s state-owned copper mining company and one of the world’s largest producers of copper.
  • E. Glencore
    Glencore is a multinational commodity trading and mining company that operates extensive resource extraction and processing assets worldwide.
  • 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_69aed95b3c088190a8f85d19e6070599 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec212a1c8190aba6311630c3fd3e completed March 9, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5123802248190b03a887d3a4e762f completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b5136f96948190861a37ba72bd2f86 completed March 14, 2026, 7:51 a.m.
NED2 Entity disambiguation (via description) batch_69b513e888008190892627805d2abd50 completed March 14, 2026, 7:53 a.m.
Created at: March 9, 2026, 3:19 p.m.