Triple

T24741
Position Surface form Disambiguated ID Type / Status
Subject Cambridge, England E492 entity
Predicate hasTwinTown P919 FINISHED
Object Heidelberg
Heidelberg is a historic university city in southwestern Germany renowned for its picturesque old town, castle ruins, and one of Europe’s oldest universities.
 E15415 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: Heidelberg | Statement: [Cambridge, England, hasTwinTown, Heidelberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heidelberg
Context triple: [Cambridge, England, hasTwinTown, Heidelberg]
  • A. Ulm
    Ulm is a historic city in the German state of Baden-Württemberg, best known for its towering Gothic cathedral and as the birthplace of physicist Albert Einstein.
  • B. Nuremberg
    Nuremberg is a historic city in Bavaria, Germany, known for its medieval architecture and its role as the site of the post–World War II war crimes tribunals.
  • C. Hamburg
    Hamburg is Germany’s second-largest city and a major northern European port and cultural center on the River Elbe.
  • D. Potsdam
    Potsdam is a historic German city near Berlin, known for its palaces, parks, and role in major 20th-century diplomatic events.
  • E. Strasbourg
    Strasbourg is a major French city on the Rhine known for hosting key European institutions, including the European Parliament and the Council of Europe.
  • 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: Heidelberg
Triple: [Cambridge, England, hasTwinTown, Heidelberg]
Generated description
Heidelberg is a historic university city in southwestern Germany renowned for its picturesque old town, castle ruins, and one of Europe’s oldest universities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heidelberg
Target entity description: Heidelberg is a historic university city in southwestern Germany renowned for its picturesque old town, castle ruins, and one of Europe’s oldest universities.
  • A. Ulm
    Ulm is a historic city in the German state of Baden-Württemberg, best known for its towering Gothic cathedral and as the birthplace of physicist Albert Einstein.
  • B. Nuremberg
    Nuremberg is a historic city in Bavaria, Germany, known for its medieval architecture and its role as the site of the post–World War II war crimes tribunals.
  • C. Hamburg
    Hamburg is Germany’s second-largest city and a major northern European port and cultural center on the River Elbe.
  • D. Potsdam
    Potsdam is a historic German city near Berlin, known for its palaces, parks, and role in major 20th-century diplomatic events.
  • E. Strasbourg
    Strasbourg is a major French city on the Rhine known for hosting key European institutions, including the European Parliament and the Council of Europe.
  • 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_69a243b4ac2c8190b93c303df797b7b2 completed Feb. 28, 2026, 1:24 a.m.
NER Named-entity recognition batch_69a2466d166881908bd8513c8d09fe8d completed Feb. 28, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2aa3edb18819080634fad6c570517 completed Feb. 28, 2026, 8:41 a.m.
NEDg Description generation batch_69a2ac77ac548190898931e22b28248e completed Feb. 28, 2026, 8:51 a.m.
NED2 Entity disambiguation (via description) batch_69a2acfdc97c8190813cce438a8127f2 completed Feb. 28, 2026, 8:53 a.m.
Created at: Feb. 28, 2026, 1:34 a.m.