Triple

T23377964
Position Surface form Disambiguated ID Type / Status
Subject King & Spalding E593657 entity
Predicate hasOfficeIn P1268 FINISHED
Object Frankfurt, Germany NE NERFINISHED

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: Frankfurt, Germany | Statement: [King & Spalding, hasOfficeIn, Frankfurt, Germany]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frankfurt, Germany
Context triple: [King & Spalding, hasOfficeIn, Frankfurt, Germany]
  • A. Frankfurt am Main chosen
    Frankfurt am Main is a major German financial and transportation hub on the River Main, known for hosting the European Central Bank and one of Europe’s busiest airports.
  • B. Frankfort, Germany
    Frankfort, Germany is a German city whose name has been used for places abroad, including the village of Frankfort in Illinois, USA.
  • C. Frankfurt Rhine-Main
    Frankfurt Rhine-Main is a major metropolitan region in western Germany centered around Frankfurt am Main, known as a key European hub for finance, transportation, and commerce.
  • D. Oper Frankfurt
    Oper Frankfurt is a major German opera house in Frankfurt am Main, renowned for its high artistic standards and innovative productions.
  • E. For Frankfurt
    For Frankfurt is a public art installation by American conceptual artist Jenny Holzer that features her signature text-based LED displays and stone benches, engaging viewers with provocative, politically charged language in an urban setting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b526ec8190b0304c72a9010abb completed April 29, 2026, 6:22 a.m.
Created at: April 17, 2026, 5:33 p.m.