Triple

T17529126
Position Surface form Disambiguated ID Type / Status
Subject Château de Berg E426882 entity
Predicate nearbySettlement P350 FINISHED
Object Berg 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: Berg | Statement: [Château de Berg, nearbySettlement, Berg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berg
Context triple: [Château de Berg, nearbySettlement, Berg]
  • A. Berg
    Berg is a small Bavarian town on the shores of Lake Starnberg in southern Germany, known for its scenic lakeside setting and historical connections to King Ludwig II.
  • B. Berg
    Berg was a historical German territorial entity that gave its name to the later Grand Duchy of Berg in the Rhineland region.
  • C. Berg
    Berg is a surname most famously associated with Alban Berg, the influential Austrian composer of the Second Viennese School.
  • D. Berg chosen
    Berg is a small town in eastern Luxembourg that serves as the administrative center of the commune of Betzdorf.
  • E. Berge
    Berge is a Norwegian surname most notably borne by politician Gunnar Berge.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e452d81a808190ab38831ea5b73b74 completed April 19, 2026, 3:58 a.m.
Created at: April 10, 2026, 5:49 a.m.