Triple

T22926737
Position Surface form Disambiguated ID Type / Status
Subject Börjigin E569329 entity
Predicate hasAncestralFigure P5206 FINISHED
Object Alan Gua 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: Alan Gua | Statement: [Börjigin, hasAncestralFigure, Alan Gua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan Gua
Context triple: [Börjigin, hasAncestralFigure, Alan Gua]
  • A. Alan Gua chosen
    Alan Gua is a legendary ancestral figure in Mongol tradition, regarded as a mythic foremother of the Borjigin clan from which Genghis Khan descended.
  • B. Harry Leong
    Harry Leong is a character in Kevin Kwan’s "Crazy Rich Asians" series, known as the wealthy, old-money uncle of protagonist Nick Young within Singapore’s elite social circle.
  • C. Desmond Choo
    Desmond Choo is a Singaporean politician and trade union leader who serves as a Member of Parliament and a key figure in the National Trades Union Congress (NTUC).
  • D. Alvin Leong
    Alvin Leong is a music producer known for his work on the song "Shall We Talk."
  • E. Gabriel Goh
    Gabriel Goh is a machine learning researcher known for his work at OpenAI, including co-developing the CLIP model for connecting images and text.
  • 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_69e2458f7d008190901dccbaebeaba24 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180d90a9481908ea10019980b3951 completed April 29, 2026, 3:54 a.m.
Created at: April 17, 2026, 3:43 p.m.