Triple

T6201406
Position Surface form Disambiguated ID Type / Status
Subject Bezirk Rostock E138640 entity
Predicate contains P35 FINISHED
Object Bad Doberan
Bad Doberan is a historic spa town in northern Germany known for its medieval Doberan Minster and proximity to the Baltic Sea coast.
E575884 NE FINISHED

How this triple was built (4 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: Bad Doberan | Statement: [Bezirk Rostock, contains, Bad Doberan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bad Doberan
Context triple: [Bezirk Rostock, contains, Bad Doberan]
  • A. Bad Oeynhausen
    Bad Oeynhausen is a spa town in North Rhine-Westphalia, Germany, renowned for its thermal springs and health resorts.
  • B. Bad Segeberg
    Bad Segeberg is a small spa town in northern Germany best known for its limestone caves and annual Karl May Festival.
  • C. Bad Nauheim
    Bad Nauheim is a spa town in the German state of Hesse, historically known for its therapeutic mineral springs and health resorts.
  • D. Bad Rothenfelde
    Bad Rothenfelde is a spa town in Lower Saxony, Germany, known for its saline springs and health resort facilities.
  • E. Bad Tölz
    Bad Tölz is a Bavarian spa town in southern Germany known for its historic old town, alpine scenery, and traditional German architecture.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bad Doberan
Triple: [Bezirk Rostock, contains, Bad Doberan]
Generated description
Bad Doberan is a historic spa town in northern Germany known for its medieval Doberan Minster and proximity to the Baltic Sea coast.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bad Doberan
Target entity description: Bad Doberan is a historic spa town in northern Germany known for its medieval Doberan Minster and proximity to the Baltic Sea coast.
  • A. Bad Oeynhausen
    Bad Oeynhausen is a spa town in North Rhine-Westphalia, Germany, renowned for its thermal springs and health resorts.
  • B. Bad Segeberg
    Bad Segeberg is a small spa town in northern Germany best known for its limestone caves and annual Karl May Festival.
  • C. Bad Nauheim
    Bad Nauheim is a spa town in the German state of Hesse, historically known for its therapeutic mineral springs and health resorts.
  • D. Bad Rothenfelde
    Bad Rothenfelde is a spa town in Lower Saxony, Germany, known for its saline springs and health resort facilities.
  • E. Bad Tölz
    Bad Tölz is a Bavarian spa town in southern Germany known for its historic old town, alpine scenery, and traditional German architecture.
  • F. None of above. chosen

Provenance (5 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_69c008acbea48190991c6b834bb45d65 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062559bcc81908942bb4d25fe8158 completed March 22, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16f366cfc81909cca73677268821a completed March 23, 2026, 4:49 p.m.
NEDg Description generation batch_69c1e375c5948190ad166089e866694a completed March 24, 2026, 1:05 a.m.
NED2 Entity disambiguation (via description) batch_69c1e43fa8348190a2247996d88b5011 completed March 24, 2026, 1:09 a.m.
Created at: March 22, 2026, 4:20 p.m.