Triple

T4258187
Position Surface form Disambiguated ID Type / Status
Subject Bob Young E96032 entity
Predicate employer P7 FINISHED
Object Lulu.com E423360 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: Lulu.com | Statement: [Bob Young, employer, Lulu.com]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lulu.com
Context triple: [Bob Young, employer, Lulu.com]
  • A. Lulu.com chosen
    Lulu.com is an online self-publishing platform that enables authors to create, publish, and distribute their books in print and digital formats.
  • B. Alibaba.com
    Alibaba.com is a leading global online business-to-business (B2B) marketplace that connects suppliers, primarily manufacturers and wholesalers, with buyers around the world.
  • C. Lazada
    Lazada is a leading Southeast Asian e-commerce platform offering a wide range of products through online marketplaces in multiple countries across the region.
  • D. Portal del Comercio
    Portal del Comercio is a historic commercial arcade or portico that lines one side of Plaza de la Constitución, housing shops and businesses under its covered walkways.
  • E. Taobao
    Taobao is a major Chinese online shopping platform known for its vast marketplace of consumer-to-consumer and business-to-consumer goods.
  • 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_69b3454095ac81909c2494f7ff294af1 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34f7ec4508190a5067f1112ac7dca completed March 12, 2026, 11:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b78422a88190a67921ee38638ac8 completed March 14, 2026, 7:31 p.m.
Created at: March 12, 2026, 11:06 p.m.