Triple

T241627
Position Surface form Disambiguated ID Type / Status
Subject Amazon E4942 entity
Predicate originalName P65 FINISHED
Object Cadabra, Inc.
Cadabra, Inc. was the original name of the company that later became Amazon, the multinational e-commerce and technology giant founded by Jeff Bezos.
 E31221 NE FINISHED

How this triple was built (4 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: Cadabra, Inc. | Statement: [Amazon, originalName, Cadabra, Inc.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cadabra, Inc.
Context triple: [Amazon, originalName, Cadabra, Inc.]
  • A. Obvious Corporation
    Obvious Corporation was the early holding company and development vehicle created by Twitter’s founders that incubated and spun out Twitter as an independent company.
  • B. Habana Labs
    Habana Labs is an Israeli-based company specializing in artificial intelligence accelerators and deep learning processors for data centers.
  • C. Oath Inc.
    Oath Inc. was a Verizon-owned digital media and advertising company formed from the merger of AOL and Yahoo.
  • D. Onex
    Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
  • E. PlumpJack Group
    PlumpJack Group is a hospitality and lifestyle company known for its wineries, hotels, restaurants, and retail businesses, originally launched in San Francisco.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cadabra, Inc.
Triple: [Amazon, originalName, Cadabra, Inc.]
Generated description
Cadabra, Inc. was the original name of the company that later became Amazon, the multinational e-commerce and technology giant founded by Jeff Bezos.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cadabra, Inc.
Target entity description: Cadabra, Inc. was the original name of the company that later became Amazon, the multinational e-commerce and technology giant founded by Jeff Bezos.
  • A. Obvious Corporation
    Obvious Corporation was the early holding company and development vehicle created by Twitter’s founders that incubated and spun out Twitter as an independent company.
  • B. Habana Labs
    Habana Labs is an Israeli-based company specializing in artificial intelligence accelerators and deep learning processors for data centers.
  • C. Oath Inc.
    Oath Inc. was a Verizon-owned digital media and advertising company formed from the merger of AOL and Yahoo.
  • D. Onex
    Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
  • E. PlumpJack Group
    PlumpJack Group is a hospitality and lifestyle company known for its wineries, hotels, restaurants, and retail businesses, originally launched in San Francisco.
  • F. None of above. chosen

Provenance (5 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_69a257c3d0708190b0871c4269d273e6 completed Feb. 28, 2026, 2:49 a.m.
NER Named-entity recognition batch_69a25cee6f208190b996be4faa700910 completed Feb. 28, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a36960563881908ef098239cd87291 completed Feb. 28, 2026, 10:17 p.m.
NEDg Description generation batch_69a369d3b3448190bcf799ec9f4f8f76 completed Feb. 28, 2026, 10:18 p.m.
NED2 Entity disambiguation (via description) batch_69a36a3215508190be525ec8625e9a9f completed Feb. 28, 2026, 10:20 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.