Triple

T12191352
Position Surface form Disambiguated ID Type / Status
Subject Victory Column E290469 entity
Predicate architect P184 FINISHED
Object Heinrich Strack E255727 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: Heinrich Strack | Statement: [Victory Column, architect, Heinrich Strack]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heinrich Strack
Context triple: [Victory Column, architect, Heinrich Strack]
  • A. Johann Heinrich Strack chosen
    Johann Heinrich Strack was a 19th-century German architect known for his significant contributions to Berlin’s neoclassical and historicist architecture.
  • B. Wilhelm Barth
    Wilhelm Barth is a mathematician known for being a doctoral student of the influential German topologist Friedrich Hirzebruch.
  • C. Wilhelm Meyer-Lübke
    Wilhelm Meyer-Lübke was a prominent Swiss linguist and Romance philologist known for his influential work on the historical development of the Romance languages.
  • D. Wilhelm Jaeger
    Wilhelm Jaeger was a German industrialist who stood trial as one of the accused in the post–World War II Krupp Trial for his role in the Nazi-era armaments industry.
  • E. Friedrich Foertsch
    Friedrich Foertsch was a German military officer who served as a Wehrmacht general during World War II and later became a high-ranking commander in the postwar West German Bundeswehr.
  • 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_69d6ab64de5881908d56eb7a75c6cc69 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c5340248190b79379423f3a3ca1 completed April 10, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f716afa8008190b4c518dd6004d87a completed May 3, 2026, 9:34 a.m.
Created at: April 8, 2026, 9:50 p.m.