Triple

T19223678
Position Surface form Disambiguated ID Type / Status
Subject Michael Moritz E480681 entity
Predicate investedIn P17330 FINISHED
Object Instacart 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: Instacart | Statement: [Michael Moritz, investedIn, Instacart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Instacart
Context triple: [Michael Moritz, investedIn, Instacart]
  • A. Instacart chosen
    Instacart is a U.S.-based grocery delivery and pickup service that partners with local retailers to let customers order groceries online for same-day fulfillment.
  • B. Shipt
    Shipt is a same-day delivery and personal shopping service that partners with retailers to deliver groceries and household essentials to customers.
  • C. Coupang
    Coupang is a South Korean e-commerce company often called the “Amazon of Korea,” known for its ultra-fast delivery service and dominant online retail platform.
  • D. Postmates
    Postmates is an on-demand delivery service platform that connects users with local couriers to deliver food, groceries, and other goods from nearby merchants.
  • E. DoorDash
    DoorDash is a leading American on-demand food delivery and logistics platform that connects customers with local restaurants and merchants through its mobile app and website.
  • 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_69d8e8ccb8f48190ad420098e74fb1db completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fa95743481909314fd14e2c3d189 completed April 20, 2026, 10:06 a.m.
Created at: April 10, 2026, 1:24 p.m.