Triple

T1720247
Position Surface form Disambiguated ID Type / Status
Subject SSH Communications Security E37372 entity
Predicate stockExchange P524 FINISHED
Object Nasdaq Helsinki E59623 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: Nasdaq Helsinki | Statement: [SSH Communications Security, stockExchange, Nasdaq Helsinki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nasdaq Helsinki
Context triple: [SSH Communications Security, stockExchange, Nasdaq Helsinki]
  • A. Nasdaq Helsinki chosen
    Nasdaq Helsinki is Finland’s primary stock exchange, hosting the trading of major Finnish companies and other securities.
  • B. Nasdaq Stockholm
    Nasdaq Stockholm is Sweden’s primary stock exchange, hosting the trading of shares in major Swedish and Nordic companies.
  • C. Oslo Stock Exchange
    The Oslo Stock Exchange is Norway's main securities market, where shares, bonds, and other financial instruments are traded.
  • D. Nasdaq Copenhagen
    Nasdaq Copenhagen is Denmark’s primary securities exchange, where shares of major Danish companies such as Danske Bank are listed and traded.
  • E. Euronext
    Euronext is a pan-European stock exchange group that operates major securities markets across several European countries, including the Netherlands, France, Belgium, and others.
  • 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_69a8861912dc8190931af43b4b9158a7 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63558d7c8190830cb8ee2e4a8932 completed March 6, 2026, 5:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8ae98cd88190af4dc46679b3d93f completed March 8, 2026, 2:42 p.m.
Created at: March 4, 2026, 7:30 p.m.