Triple

T1082921
Position Surface form Disambiguated ID Type / Status
Subject NDX E23986 entity
Predicate currency P245 FINISHED
Object US dollar E105 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: US dollar | Statement: [NDX, currency, US dollar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: US dollar
Context triple: [NDX, currency, US dollar]
  • A. US dollar chosen
    The US dollar is the official currency of the United States and the world’s primary reserve currency used widely in global trade and finance.
  • B. Dollar
    Dollar is a small historic town in Clackmannanshire, Scotland, known for its scenic setting near the Ochil Hills and the nearby Castle Campbell.
  • C. gold dollar
    The gold dollar was a small U.S. gold coin minted in the mid-19th century, notable as the smallest-denomination gold coin ever issued by the United States.
  • D. Pound sterling
    The pound sterling is the official currency of the United Kingdom and one of the world’s oldest continuously used monetary units.
  • E. Bahamian dollar
    The Bahamian dollar is the official currency of The Bahamas, pegged to the U.S. dollar and used throughout the archipelago for everyday transactions and tourism.
  • 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_69a493f1ddf48190a99d54b00e99f8ce completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b95e56948190a1e92367ad7240b7 completed March 1, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac538a5d248190bb44c6b27d2c714c completed March 7, 2026, 4:34 p.m.
Created at: March 1, 2026, 7:42 p.m.