Triple

T3635129
Position Surface form Disambiguated ID Type / Status
Subject Panzer I E77048 entity
Predicate manufacturer P490 FINISHED
Object Krupp E31323 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: Krupp | Statement: [Panzer I, manufacturer, Krupp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Krupp
Context triple: [Panzer I, manufacturer, Krupp]
  • A. Krupp (company) chosen
    Krupp (company) was a major German industrial conglomerate best known for its steel production and armaments manufacturing, playing a central role in both World Wars and in the development of heavy industry in Germany.
  • B. Borsigwerke
    Borsigwerke is a Berlin U-Bahn station on line U6 serving the Tegel district in the city’s northwest.
  • C. Deutsche Werft AG
    Deutsche Werft AG was a German shipbuilding company based in Hamburg, known for constructing naval vessels and submarines, particularly during the World War II era.
  • D. Blohm & Voss
    Blohm & Voss is a German shipbuilding and engineering company renowned for constructing major naval vessels and later aircraft, particularly during the World Wars.
  • E. Henschel & Sohn
    Henschel & Sohn was a German engineering and manufacturing company best known for producing heavy military vehicles, including tanks, during World War II.
  • 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_69ad85dd0be48190b738990cb20c4731 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc325e2548190ae243ae69126e65c completed March 8, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f1ec2bc8190ae88a2010f84e998 completed March 13, 2026, 5:53 p.m.
Created at: March 8, 2026, 3:24 p.m.