Triple

T9844891
Position Surface form Disambiguated ID Type / Status
Subject Breakthrough Prize Foundation E239315 entity
Predicate foundedBy P104 FINISHED
Object Cathy Zhang E239314 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: Cathy Zhang | Statement: [Breakthrough Prize Foundation, foundedBy, Cathy Zhang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cathy Zhang
Context triple: [Breakthrough Prize Foundation, foundedBy, Cathy Zhang]
  • A. Cathy Zhang
    Cathy Zhang is a Chinese entrepreneur best known as a founder of the multinational technology conglomerate Alibaba Group.
  • B. Cathy Zhang chosen
    Cathy Zhang is a founder associated with the prestigious Breakthrough Prize in Life Sciences, an award recognizing major advances in biological and medical research.
  • C. Eugenia Yuan
    Eugenia Yuan is a Hong Kong–born American actress and former rhythmic gymnast known for her roles in international martial arts and drama films.
  • D. Caroline Zhang
    Caroline Zhang is an American figure skater known for her lyrical style, strong spins, and success on the international junior circuit in the late 2000s.
  • E. Cathy Shim
    Cathy Shim is an American actress, comedian, and writer known for her work in sketch comedy and television, including appearances on shows like Reno 911!.
  • 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb35dc29c819080203be5b904dc9d completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5dda4b0819092703270e87bee5a completed April 5, 2026, 3:24 a.m.
Created at: March 30, 2026, 8:33 p.m.