Triple

T15931390
Position Surface form Disambiguated ID Type / Status
Subject Goldmark E386331 entity
Predicate replaced P101 FINISHED
Object Hamburg mark banco E889800 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: Hamburg mark banco | Statement: [Goldmark, replaced, Hamburg mark banco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hamburg mark banco
Context triple: [Goldmark, replaced, Hamburg mark banco]
  • A. Hamburg banco
    Hamburg banco was a stable silver-based bank money used in early modern Hamburg as a key medium for large-scale and international trade transactions.
  • B. Hamburg mark chosen
    The Hamburg mark was the historical monetary unit used by the Free City of Hamburg before the adoption of the German mark.
  • C. Frankfurter Bank
    Frankfurter Bank was a historic German financial institution based in Frankfurt that played a key role in early 20th-century banking and corporate finance.
  • D. Königsberger Bank
    Königsberger Bank was a historic German financial institution based in Königsberg that played a key role in regional banking and early 20th-century commercial development.
  • E. Hamburglar
    Hamburglar is a classic McDonaldland villain character known for his striped outfit, wide-brimmed hat, and comical attempts to steal hamburgers.
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156a5b9348190962ddc1c35caf44f completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5b2a8888190824f2252b65920f2 completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:52 a.m.