Triple

T281876
Position Surface form Disambiguated ID Type / Status
Subject Dutch guilder E5370 entity
Predicate ISO4217Code P189 FINISHED
Object NLG
NLG was the ISO 4217 currency code for the Dutch guilder, the former national currency of the Netherlands before the adoption of the euro.
E36858 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: NLG | Statement: [Dutch guilder, ISO4217Code, NLG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NLG
Context triple: [Dutch guilder, ISO4217Code, NLG]
  • A. NLS
    NLS (oN-Line System) was an early, pioneering computer system that introduced many foundational concepts of modern computing, including the mouse, hypertext, and collaborative editing.
  • B. NLS
    NLS is a U.S. Library of Congress program that provides free accessible reading materials, including braille and audio books, to people who are blind, have low vision, or are print disabled.
  • C. Grok
    Grok is an AI chatbot developed by xAI, designed to provide conversational access to real-time information and reasoning capabilities.
  • D. Versoix
    Versoix is a Swiss municipality on the shores of Lake Geneva, known as a residential suburb of Geneva with lakeside promenades and a mix of urban and natural landscapes.
  • E. GPT-3
    GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
  • 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: NLG
Triple: [Dutch guilder, ISO4217Code, NLG]
Generated description
NLG was the ISO 4217 currency code for the Dutch guilder, the former national currency of the Netherlands before the adoption of the euro.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: NLG
Target entity description: NLG was the ISO 4217 currency code for the Dutch guilder, the former national currency of the Netherlands before the adoption of the euro.
  • A. NLS
    NLS (oN-Line System) was an early, pioneering computer system that introduced many foundational concepts of modern computing, including the mouse, hypertext, and collaborative editing.
  • B. NLS
    NLS is a U.S. Library of Congress program that provides free accessible reading materials, including braille and audio books, to people who are blind, have low vision, or are print disabled.
  • C. Grok
    Grok is an AI chatbot developed by xAI, designed to provide conversational access to real-time information and reasoning capabilities.
  • D. Versoix
    Versoix is a Swiss municipality on the shores of Lake Geneva, known as a residential suburb of Geneva with lakeside promenades and a mix of urban and natural landscapes.
  • E. GPT-3
    GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
  • 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_69a257e6c8788190987dfe705ca2912a completed Feb. 28, 2026, 2:50 a.m.
NER Named-entity recognition batch_69a25e0a23c0819083abee28b2dea49c completed Feb. 28, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69a399a74d448190a4857ce008e64e7e completed March 1, 2026, 1:43 a.m.
NEDg Description generation batch_69a39a161064819096fd8f4efe533538 completed March 1, 2026, 1:44 a.m.
NED2 Entity disambiguation (via description) batch_69a39a7c0cec81909f737bd963ad306d completed March 1, 2026, 1:46 a.m.
Created at: Feb. 28, 2026, 2:59 a.m.