Triple

T636667
Position Surface form Disambiguated ID Type / Status
Subject Dan Kan E16636 entity
Predicate coFounded P104 FINISHED
Object Cruise Automation E2753 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: Cruise Automation | Statement: [Dan Kan, coFounded, Cruise Automation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cruise Automation
Context triple: [Dan Kan, coFounded, Cruise Automation]
  • A. Autopilot
    Autopilot is Tesla’s advanced driver-assistance system designed to automate steering, acceleration, and braking under driver supervision.
  • B. Cruise LLC chosen
    Cruise LLC is an autonomous vehicle company focused on developing and deploying self-driving car technology, particularly for urban ride-hailing services.
  • C. Chessie System
    Chessie System was a major American railroad holding company formed in the 1970s that operated several eastern U.S. railroads under the iconic “Chessie the cat” branding before eventually becoming part of CSX Transportation.
  • D. Voyager KC2
    Voyager KC2 is an Airbus A330-based multi-role tanker transport aircraft used by the Royal Air Force for air-to-air refuelling and strategic airlift operations.
  • E. Element AI
    Element AI was a Montreal-based artificial intelligence company and research lab known for developing enterprise AI solutions and advancing deep learning research.
  • 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_69a4936be1c88190af56540324b57da7 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49ee7fdbc8190858e42bb1bfdb3ff completed March 1, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5778daa0881908311823d8db543ae completed March 2, 2026, 11:42 a.m.
Created at: March 1, 2026, 7:35 p.m.