Triple

T386058
Position Surface form Disambiguated ID Type / Status
Subject Vistula–Oder Offensive E8781 entity
Predicate notableCityCaptured P8411 FINISHED
Object Warsaw E8399 NE FINISHED

How this triple was built (3 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: Warsaw | Statement: [Vistula–Oder Offensive, notableCityCaptured, Warsaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Warsaw
Context triple: [Vistula–Oder Offensive, notableCityCaptured, Warsaw]
  • A. Warsaw chosen
    Warsaw is the capital and largest city of Poland, known for its resilient history, especially its near-total destruction in World War II and subsequent postwar reconstruction.
  • B. Lublin
    Lublin is a historic city in eastern Poland known as a major cultural, academic, and economic center and for its significant role in Polish political history.
  • C. Kraków
    Kraków is one of Poland’s oldest and most historically significant cities, renowned for its well-preserved medieval core, royal heritage, and cultural institutions.
  • D. Wilno
    Wilno is the historical Polish name for Vilnius, a major cultural and political center of the region that served as an important city in the interwar Second Polish Republic.
  • E. Łódź
    Łódź is one of Poland’s largest cities, historically known as a major industrial and textile manufacturing center.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableCityCaptured
Context triple: [Vistula–Oder Offensive, notableCityCaptured, Warsaw]
  • A. conqueredCity
    Indicates that one entity has taken control of a city from another entity, typically through military force or domination.
  • B. dateOfCityCapture
    Indicates the specific date on which a city was taken or captured, typically in a military or political context.
  • C. capturedPlace chosen
    Indicates that an agent took control of or seized a specific place, typically through force or strategic action.
  • D. mainCityDestroyed
    Indicates that the primary or central city associated with an entity has been destroyed.
  • E. cityOwned
    Indicates that something is owned, managed, or under the jurisdiction of a city or municipal government.
  • F. None of above.

Provenance (4 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_69a2e7f47dd08190a4e294ccbbe46cd4 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec447b5481908a5a084787b44ced completed Feb. 28, 2026, 1:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4429d10d88190ac5407bf4e539d4f completed March 1, 2026, 1:43 p.m.
PD Predicate disambiguation batch_69a2e967d84c8190a6b647f78d95d4e4 completed Feb. 28, 2026, 1:11 p.m.
Created at: Feb. 28, 2026, 1:08 p.m.