Triple

T13165608
Position Surface form Disambiguated ID Type / Status
Subject Germania Inferior E312841 entity
Predicate hadLegionaryBase P50573 FINISHED
Object Vetera E553880 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: Vetera | Statement: [Germania Inferior, hadLegionaryBase, Vetera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vetera
Context triple: [Germania Inferior, hadLegionaryBase, Vetera]
  • A. Vetera chosen
    Vetera was a major Roman legionary fortress and military base on the Rhine frontier in the province of Germania Inferior.
  • B. Geltow
    Geltow is a village in the German state of Brandenburg, known as a district of the municipality Schwielowsee near Potsdam.
  • C. Adiutrix
    Adiutrix is the Latin term meaning "helper" or "assistant," historically associated with the Roman legion Legio I Adiutrix and reflecting its supportive military role.
  • D. Hæren
    Hæren is the land warfare branch of Norway’s armed forces, responsible for ground-based military operations and national defense.
  • E. Vojak
    Vojak is the highest peak of the Učka mountain range in Croatia, offering panoramic views over the Istrian peninsula and the Adriatic Sea.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c0bf5a48190bf245dceee24b579 completed April 10, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eaf6c9ec8190bc0097d62e57e52a completed May 3, 2026, 6:28 a.m.
Created at: April 9, 2026, 9:13 p.m.