Triple

T9834538
Position Surface form Disambiguated ID Type / Status
Subject Berlin Nordufer campus E239066 entity
Predicate locatedOn P40 FINISHED
Object Nordufer
Nordufer is a street and riverside area in Berlin, Germany, running along the banks of the River Spree in the district of Wedding.
 E825263 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: Nordufer | Statement: [Berlin Nordufer campus, locatedOn, Nordufer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nordufer
Context triple: [Berlin Nordufer campus, locatedOn, Nordufer]
  • A. Ehrwald
    Ehrwald is a picturesque Austrian village in Tyrol, known as a popular alpine resort and gateway to the Zugspitze massif.
  • B. Givlaari
    Givlaari is an RNA interference-based therapy used to treat acute hepatic porphyria by reducing the production of toxic heme intermediates in the liver.
  • C. Norén
    Norén is a Swedish surname, notably borne by actress Noomi Rapace before she adopted her stage name.
  • D. Badeloch
    Badeloch is a central female character in Joost van den Vondel’s Dutch play "Gijsbrecht van Aemstel," known as the loyal and tragic wife of the title hero.
  • E. Aldan
    Aldan is a mining town in Russia’s Sakha Republic known for its significant gold deposits and remote Siberian location.
  • 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: Nordufer
Triple: [Berlin Nordufer campus, locatedOn, Nordufer]
Generated description
Nordufer is a street and riverside area in Berlin, Germany, running along the banks of the River Spree in the district of Wedding.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nordufer
Target entity description: Nordufer is a street and riverside area in Berlin, Germany, running along the banks of the River Spree in the district of Wedding.
  • A. Ehrwald
    Ehrwald is a picturesque Austrian village in Tyrol, known as a popular alpine resort and gateway to the Zugspitze massif.
  • B. Givlaari
    Givlaari is an RNA interference-based therapy used to treat acute hepatic porphyria by reducing the production of toxic heme intermediates in the liver.
  • C. Norén
    Norén is a Swedish surname, notably borne by actress Noomi Rapace before she adopted her stage name.
  • D. Badeloch
    Badeloch is a central female character in Joost van den Vondel’s Dutch play "Gijsbrecht van Aemstel," known as the loyal and tragic wife of the title hero.
  • E. Aldan
    Aldan is a mining town in Russia’s Sakha Republic known for its significant gold deposits and remote Siberian location.
  • 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_69ca84e314108190978324a4bdb959f8 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb3385054819094145c96204e3f0d completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5c8f1a48190a4e7b6cda8ee88d5 completed April 5, 2026, 3:23 a.m.
NEDg Description generation batch_69d1d6a385ac8190b5dd11adfbb7578d completed April 5, 2026, 3:27 a.m.
NED2 Entity disambiguation (via description) batch_69d1d74e7a148190a9470745bfd7ad42 completed April 5, 2026, 3:30 a.m.
Created at: March 30, 2026, 8:32 p.m.