Triple

T17963345
Position Surface form Disambiguated ID Type / Status
Subject Pravin Gordhan E449137 entity
Predicate familyName P18 FINISHED
Object Gordhan 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: Gordhan | Statement: [Pravin Gordhan, familyName, Gordhan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gordhan
Context triple: [Pravin Gordhan, familyName, Gordhan]
  • A. Gordhan chosen
    Gordhan is the surname of Pravin Gordhan, a prominent South African politician and former finance minister.
  • B. Yadnya Kasada
    Yadnya Kasada is a traditional Tenggerese Hindu ritual in which offerings are cast into the crater of Mount Bromo in East Java, Indonesia, to honor ancestral spirits and deities.
  • C. Gopinath
    Gopinath is a masculine given name commonly used in India, often associated with cultural, religious, and historical figures.
  • D. Ben Indra
    Ben Indra is an American actor known for his supporting roles in film and television and for his former marriage to actress Anna Faris.
  • E. Mahendra
    Mahendra is a central fictional character in Rabindranath Tagore’s Bengali novel "Chokher Bali," whose complex relationships drive much of the story’s emotional conflict.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b135cd2c8190a6190cf6611dbe08 completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.