Triple

T22780834
Position Surface form Disambiguated ID Type / Status
Subject Robert Mangaliso Sobukwe E563830 entity
Predicate hasMiddleName P143 FINISHED
Object Mangaliso NE NERFINISHED

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: Mangaliso | Statement: [Robert Mangaliso Sobukwe, hasMiddleName, Mangaliso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangaliso
Context triple: [Robert Mangaliso Sobukwe, hasMiddleName, Mangaliso]
  • A. Mangaliso chosen
    Mangaliso is the middle name of Robert Sobukwe, the prominent South African anti-apartheid activist and founding leader of the Pan Africanist Congress.
  • B. Marangona
    Marangona is the largest and most famous bell of St Mark's Campanile in Venice, traditionally used to mark the beginning and end of the working day and to signal important civic events.
  • C. Mangaya
    Mangaya is an exonym referring to the Mandaya, an indigenous ethnic group of Mindanao in the southern Philippines known for their rich weaving traditions and upland farming.
  • D. Mangilao
    Mangilao is a village on the eastern side of Guam known for hosting the University of Guam and Guam Community College.
  • E. Malango
    Malango is an Oceanic language spoken in the Solomon Islands, closely related to and geographically adjacent to the Ghari language.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2455500788190b4b33030461f3bbd completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17c2cab0881908df1d0629b43d350 completed April 29, 2026, 3:34 a.m.
Created at: April 17, 2026, 3:28 p.m.