Triple

T5397289
Position Surface form Disambiguated ID Type / Status
Subject UM E120686 entity
Predicate districtSeat P61277 FINISHED
Object Prenzlau E163379 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: Prenzlau | Statement: [UM, districtSeat, Prenzlau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prenzlau
Context triple: [UM, districtSeat, Prenzlau]
  • A. Prenzlau chosen
    Prenzlau is a historic town in northeastern Germany’s Brandenburg region, known for its medieval architecture and role as a regional administrative center.
  • B. Fürstenwalde
    Fürstenwalde is a town in eastern Germany’s Brandenburg region, known for its location on the River Spree and its historic churches and medieval architecture.
  • C. Riesa
    Riesa is a town in the German state of Saxony, situated on the Elbe River and known historically as an important regional railway and industrial center.
  • D. Genthin
    Genthin is a small town in the German state of Saxony-Anhalt, historically part of Prussia and known for its location along the Elbe–Havel Canal.
  • E. Zinnowitz
    Zinnowitz is a seaside resort town on Germany’s Baltic Sea coast, known for its sandy beaches, historic spa architecture, and tourism on the island of Usedom.
  • 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: districtSeat
Context triple: [UM, districtSeat, Prenzlau]
  • A. district
    Indicates that one entity is an administrative or electoral district that geographically contains or governs another entity.
  • B. districtCouncil
    Indicates that an entity serves as, or is governed by, a district-level council within a larger administrative or political structure.
  • C. countySeatLocatedAt chosen
    Indicates that a county’s administrative center or capital is located at a specific place or settlement.
  • D. districtLost
    Indicates that a district previously controlled or held by an entity has been lost, ceded, or no longer remains under that entity’s control.
  • E. servedDistrict
    Indicates that an entity has provided official service or representation to a particular district.
  • 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_69bd4637b92c8190b815b6443ae4b323 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8932b8bc8190bd31e11b167a7212 completed March 20, 2026, 5:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf77af7f0881908fad92962a2a6191 completed March 22, 2026, 5:01 a.m.
PD Predicate disambiguation batch_69bd84660ea08190a641084814fcf94d completed March 20, 2026, 5:31 p.m.
Created at: March 20, 2026, 2:04 p.m.