Triple

T11063679
Position Surface form Disambiguated ID Type / Status
Subject Medea Benjamin E261567 entity
Predicate associatedOrganization P37 FINISHED
Object Global Exchange E903081 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: Global Exchange | Statement: [Medea Benjamin, associatedOrganization, Global Exchange]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Global Exchange
Context triple: [Medea Benjamin, associatedOrganization, Global Exchange]
  • A. Global Exchange chosen
    Global Exchange is an international human rights organization and advocacy group focused on promoting social, economic, and environmental justice worldwide.
  • B. Global Exchange Market
    The Global Exchange Market is a trading platform operated by the Irish Stock Exchange that facilitates the listing and trading of securities for international issuers.
  • C. Global Hub
    Global Hub is the flagship, state-of-the-art campus building of Northwestern University's Kellogg School of Management, designed to support collaborative, innovative business education.
  • D. Global
    Global is a major UK-based media and entertainment company best known for owning and operating prominent radio brands and digital audio platforms.
  • E. International Market
    International Market is a large, historic traditional market in Busan, South Korea, known for its dense network of stalls selling a wide variety of goods and its origins in the post-Korean War era.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d798ed07f88190bf501d9f63386ada completed April 9, 2026, 12:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3e75b90ec8190b1a799e0183c6784 completed April 18, 2026, 8:19 p.m.
Created at: April 8, 2026, 9:26 p.m.