Triple

T9975947
Position Surface form Disambiguated ID Type / Status
Subject Duke of Bremen-Verden E196327 entity
Predicate capital P234 FINISHED
Object Stade E222954 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: Stade | Statement: [Duke of Bremen-Verden, capital, Stade]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stade
Context triple: [Duke of Bremen-Verden, capital, Stade]
  • A. Stade chosen
    Stade is a historic Hanseatic town in northern Germany known for its medieval harbor, brick Gothic architecture, and role as a former trading center on the Elbe River.
  • B. Stade d’Octodure
    Stade d’Octodure is a sports stadium in Martigny, Switzerland, primarily used for football and athletics events.
  • C. Stade Bauer
    Stade Bauer is a historic football stadium in Saint-Ouen-sur-Seine, France, best known as the longtime home ground of Red Star FC.
  • D. Stadion
    Stadion is a Stockholm metro station on the red line, known for its colorful rainbow-themed artwork and proximity to the Stockholm Olympic Stadium.
  • E. Stade Auguste-Bonal
    Stade Auguste-Bonal is a football stadium in Montbéliard, France, best known as the long-time home ground of FC Sochaux-Montbéliard.
  • 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_69ca82eea2b88190a0e511d21a31f386 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb84b47308190aa2f94fa7320cdc3 completed April 2, 2026, 12:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23de601f0819096004bf60ffa2d2c completed April 5, 2026, 10:48 a.m.
Created at: March 30, 2026, 8:48 p.m.