Triple

T13161944
Position Surface form Disambiguated ID Type / Status
Subject Upper Sorbian E312747 entity
Predicate writingSystem P454 FINISHED
Object Upper Sorbian alphabet E312747 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: Upper Sorbian alphabet | Statement: [Upper Sorbian, writingSystem, Upper Sorbian alphabet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Upper Sorbian alphabet
Context triple: [Upper Sorbian, writingSystem, Upper Sorbian alphabet]
  • A. Upper Sorbian chosen
    Upper Sorbian is a West Slavic minority language spoken primarily in eastern Germany, especially in the region of Upper Lusatia.
  • B. Lower Sorbian
    Lower Sorbian is a West Slavic minority language spoken primarily in eastern Germany, especially in the Lower Lusatia region of Brandenburg.
  • C. Sorbian languages
    The Sorbian languages are a pair of closely related West Slavic minority languages spoken by the Sorb community primarily in eastern Germany, especially in Lusatia.
  • D. Slovak alphabet
    The Slovak alphabet is the standardized set of Latin-based letters with diacritics used to write the Slovak language.
  • E. Altsächsisch
    Altsächsisch is a historical West Germanic language spoken by the Saxons in what is now northern Germany and parts of the Netherlands during the early Middle Ages.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c0a9d348190909fcf45f9d650e4 completed April 10, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eaf4cd788190b74cca51b5219bfb completed May 3, 2026, 6:28 a.m.
Created at: April 9, 2026, 9:12 p.m.