Triple

T16231963
Position Surface form Disambiguated ID Type / Status
Subject Keith Rabois E394004 entity
Predicate notableWork P4 FINISHED
Object Khosla Ventures E351366 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: Khosla Ventures | Statement: [Keith Rabois, notableWork, Khosla Ventures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khosla Ventures
Context triple: [Keith Rabois, notableWork, Khosla Ventures]
  • A. Khosla Ventures chosen
    Khosla Ventures is a Silicon Valley-based venture capital firm known for investing in early-stage, high-risk technology and clean energy startups.
  • B. Sequoia Capital
    Sequoia Capital is a leading Silicon Valley venture capital firm known for early investments in companies like Apple, Google, and Airbnb.
  • C. 500 Startups
    500 Startups is a global venture capital firm and startup accelerator known for investing in and mentoring early-stage technology companies around the world.
  • D. Thiel Capital
    Thiel Capital is an investment firm and family office managing the personal capital and strategic ventures of billionaire entrepreneur and investor Peter Thiel.
  • E. Kapor Capital
    Kapor Capital is an early-stage venture capital firm focused on investing in technology-driven startups that aim to close gaps in access, opportunity, and outcomes for underserved communities.
  • 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_69d87f204df88190a8f88923decf9835 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e23d29fa248190943f4c3f7808908b completed April 17, 2026, 2:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0007a0ab08819082aea4c312c9ffc7 completed May 10, 2026, 4:20 a.m.
Created at: April 10, 2026, 5:04 a.m.