Triple

T15746495
Position Surface form Disambiguated ID Type / Status
Subject Red Army units E381732 entity
Predicate garrison P75 FINISHED
Object Orel E191974 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: Orel | Statement: [Red Army units, garrison, Orel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orel
Context triple: [Red Army units, garrison, Orel]
  • A. Orel
    Orel is a male given name most famously associated with former Major League Baseball pitcher Orel Hershiser.
  • B. Ostan
    Ostan was a historic city that served as the political and administrative center of the medieval Armenian region of Vaspurakan.
  • C. Ngawi
    Ngawi is a regency capital and regional town in East Java, Indonesia, known as a transportation hub and gateway between Central and East Java.
  • D. Dunellen
    Dunellen is a small borough in central New Jersey known for its residential character and commuter access to the New York metropolitan area.
  • E. Orel salient chosen
    The Orel salient was a German-held bulge in the Eastern Front lines around the city of Orel in World War II, which became the focus of a major Soviet counteroffensive following the Battle of Kursk.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0502d72008190b4d13a6b3a12e467 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8309cba881909579ee5a62b3aa31 completed May 9, 2026, 6:55 p.m.
Created at: April 10, 2026, 4:46 a.m.