Triple

T8040644
Position Surface form Disambiguated ID Type / Status
Subject Kölsch E187426 entity
Predicate altName P39 FINISHED
Object Colognian E128558 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: Colognian | Statement: [Kölsch, altName, Colognian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Colognian
Context triple: [Kölsch, altName, Colognian]
  • A. Colognian chosen
    Colognian is a Central Ripuarian Franconian dialect of German spoken primarily in and around the city of Cologne.
  • B. Eastphalian
    Eastphalian is a regional variety of Low German traditionally spoken in parts of central northern Germany, particularly around the historical region of Eastphalia.
  • C. Frankfurter
    Frankfurter is a Jewish Ashkenazi toponymic surname originally denoting a person from the city of Frankfurt in Germany.
  • D. Sorbs
    The Sorbs are a Slavic ethnic minority primarily living in eastern Germany, known for preserving their distinct Sorbian language and cultural traditions.
  • E. Oldenburger
    Oldenburger is a surname most notably associated with Rufus Oldenburger, an American mathematician and engineer known for his work in control theory and applied mathematics.
  • 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_69ca82b00cb48190b59a300f70e97bd7 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3f1d62c48190bf4a6cd17517c5dc completed March 31, 2026, 3:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc5706a4a881909758ea34cf5c0cf2 completed March 31, 2026, 11:21 p.m.
Created at: March 30, 2026, 5:23 p.m.