Triple

T8938603
Position Surface form Disambiguated ID Type / Status
Subject Michael Aris E212838 entity
Predicate twin P2516 FINISHED
Object Anthony Aris E769407 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: Anthony Aris | Statement: [Michael Aris, twin, Anthony Aris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Aris
Context triple: [Michael Aris, twin, Anthony Aris]
  • A. Anthony Aris chosen
    Anthony Aris was a British Tibetologist, publisher, and scholar known for his contributions to the study and preservation of Tibetan culture and history.
  • B. Michael Aris
    Michael Aris was a British historian and scholar of Tibetan and Himalayan studies, best known as the late husband of Burmese political leader and Nobel laureate Aung San Suu Kyi.
  • C. Alexander Aris
    Alexander Aris is the son of Burmese democracy leader Aung San Suu Kyi and British academic Michael Aris, known for his connection to his mother's political legacy.
  • D. Robert Drivas
    Robert Drivas was an American actor and director best known for his character roles in film, television, and theater during the 1960s and 1970s.
  • E. George Letsas
    George Letsas is a legal scholar and professor known for his work in legal philosophy and human rights law.
  • 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_69ca839694c88190b324ffeb43d23b08 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66b57a348190979effe4f9998eb7 completed April 1, 2026, 12:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd099b2f48190b81d6747bad4b992 completed April 3, 2026, 2:37 p.m.
Created at: March 30, 2026, 6:58 p.m.