Triple

T3686002
Position Surface form Disambiguated ID Type / Status
Subject Spandau E78225 entity
Predicate hasSubdivision P747 FINISHED
Object Staaken
Staaken is a locality in western Berlin, Germany, known for its residential areas and historical role as part of the Spandau district near the former inner-German border.
E379226 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: Staaken | Statement: [Spandau, hasSubdivision, Staaken]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Staaken
Context triple: [Spandau, hasSubdivision, Staaken]
  • A. Hodenhagen
    Hodenhagen is a small municipality in Lower Saxony, Germany, known for its rural setting along the Aller River and proximity to attractions like the Serengeti Park safari zoo.
  • B. Boskoop
    Boskoop is a Dutch town historically renowned as a major center of tree and nursery cultivation.
  • C. Grebbestad
    Grebbestad is a coastal fishing village and popular tourist destination in Tanum Municipality on Sweden’s west coast, known for its seafood and picturesque archipelago.
  • D. Wassenaar
    Wassenaar is an affluent coastal town in the western Netherlands known for its wooded estates, beaches, and role as a residential area for diplomats and expatriates.
  • E. Noordwyk
    Noordwyk is a residential suburb located within the Midrand area of Johannesburg, South Africa.
  • 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: Staaken
Triple: [Spandau, hasSubdivision, Staaken]
Generated description
Staaken is a locality in western Berlin, Germany, known for its residential areas and historical role as part of the Spandau district near the former inner-German border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Staaken
Target entity description: Staaken is a locality in western Berlin, Germany, known for its residential areas and historical role as part of the Spandau district near the former inner-German border.
  • A. Hodenhagen
    Hodenhagen is a small municipality in Lower Saxony, Germany, known for its rural setting along the Aller River and proximity to attractions like the Serengeti Park safari zoo.
  • B. Boskoop
    Boskoop is a Dutch town historically renowned as a major center of tree and nursery cultivation.
  • C. Grebbestad
    Grebbestad is a coastal fishing village and popular tourist destination in Tanum Municipality on Sweden’s west coast, known for its seafood and picturesque archipelago.
  • D. Wassenaar
    Wassenaar is an affluent coastal town in the western Netherlands known for its wooded estates, beaches, and role as a residential area for diplomats and expatriates.
  • E. Noordwyk
    Noordwyk is a residential suburb located within the Midrand area of Johannesburg, South Africa.
  • 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_69ad85e285a081908f8cbfa9e2ed9b75 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc4c676748190b074abfb9ba43b49 completed March 8, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3bd473c8190b814689f3c76cada completed March 14, 2026, 2:11 a.m.
NEDg Description generation batch_69b4c463b53c8190b3333fda95862545 completed March 14, 2026, 2:13 a.m.
NED2 Entity disambiguation (via description) batch_69b4c4ee4db88190810a1d49d757b2b6 completed March 14, 2026, 2:16 a.m.
Created at: March 8, 2026, 3:26 p.m.