Triple

T19366103
Position Surface form Disambiguated ID Type / Status
Subject Agnes of Rochlitz E484404 entity
Predicate placeOfOrigin P3743 FINISHED
Object Rochlitz 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: Rochlitz | Statement: [Agnes of Rochlitz, placeOfOrigin, Rochlitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rochlitz
Context triple: [Agnes of Rochlitz, placeOfOrigin, Rochlitz]
  • A. Rochlitz chosen
    Rochlitz is a small historic town in the German state of Saxony, known for its medieval architecture and the prominent Rochlitz Castle overlooking the Mulde River.
  • B. Elsterwerda
    Elsterwerda is a small town in the state of Brandenburg in eastern Germany, known for its regional railway connections and location near the Elbe-Elster district.
  • C. Prenzlau
    Prenzlau is a rural locality and small town in Queensland, Australia, situated within the Somerset Region and known for its agricultural character.
  • D. Prenzlau
    Prenzlau is a historic town in northeastern Germany’s Brandenburg region, known for its medieval architecture and role as a regional administrative center.
  • E. Treuenbrietzen
    Treuenbrietzen is a historic town in the German state of Brandenburg, known for its medieval architecture and role in Reformation-era history.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619ac26d4819095836d737b629cf1 completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.