Triple

T3075713
Position Surface form Disambiguated ID Type / Status
Subject Drew Bagnell E64130 entity
Predicate employer P7 FINISHED
Object Aurora Innovation E325557 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: Aurora Innovation | Statement: [Drew Bagnell, employer, Aurora Innovation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aurora Innovation
Context triple: [Drew Bagnell, employer, Aurora Innovation]
  • A. Aurora Innovation chosen
    Aurora Innovation is an autonomous vehicle technology company focused on developing self-driving systems for cars, trucks, and other vehicles.
  • B. Aurora Network
    Aurora Network is a European university alliance focused on collaboration in research, education, and innovation among its member institutions.
  • C. Innoventions
    Innoventions was an interactive exhibit pavilion at Epcot in Walt Disney World that showcased emerging technologies and hands-on science displays.
  • D. Artemis S.A.
    Artemis S.A. is a French holding company controlled by the Pinault family, known for owning and managing major luxury, fashion, and lifestyle brands.
  • E. Onex Corporation
    Onex Corporation is a Canadian investment management firm and private equity company known for acquiring and managing businesses across various industries.
  • 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_69ad857a8aec8190bfdfd9c14554ac5a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada150d8e08190bde5f68e800e8feb completed March 8, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20357f8c48190b6874f7596f30052 completed March 12, 2026, 12:05 a.m.
Created at: March 8, 2026, 3:02 p.m.