Triple

T10880914
Position Surface form Disambiguated ID Type / Status
Subject De Beers E256914 entity
Predicate subsidiary P258 FINISHED
Object Namdeb E890434 NE FINISHED

How this triple was built (2 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: Namdeb | Statement: [De Beers, subsidiary, Namdeb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Namdeb
Context triple: [De Beers, subsidiary, Namdeb]
  • A. Namdeb chosen
    Namdeb is a diamond mining company in Namibia formed as a joint venture between the Namibian government and De Beers.
  • B. Ndar
    Ndar is the historical Wolof name for the city of Saint-Louis in Senegal, reflecting its pre-colonial and local cultural identity.
  • C. Nabaloi
    Nabaloi is an Austronesian language spoken by the Ibaloi people of the northern Philippines, particularly in the Benguet region of Luzon.
  • D. Kidepo Toposa
    Kidepo Toposa is a regional dialect of the Toposa language spoken by Toposa communities in the Kidepo area of South Sudan.
  • E. Zande
    Zande is a Central African language spoken primarily by the Azande people across parts of South Sudan, the Central African Republic, and the Democratic Republic of the Congo.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa848804819081b2713ca0bedf06 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d751b031a88190b1182dfc1f520264 completed April 9, 2026, 7:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69e154e49ab08190b522b5361ac65c01 completed April 16, 2026, 9:30 p.m.
Created at: April 8, 2026, 9:21 p.m.