Triple

T15041414
Position Surface form Disambiguated ID Type / Status
Subject Royal Djurgården park E378607 entity
Predicate hasLandmark P105 FINISHED
Object Blockhusudden
Blockhusudden is a scenic headland and residential area on the eastern tip of Djurgården in Stockholm, known for its waterfront views, historic buildings, and maritime traffic.
E1132985 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: Blockhusudden | Statement: [Royal Djurgården park, hasLandmark, Blockhusudden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blockhusudden
Context triple: [Royal Djurgården park, hasLandmark, Blockhusudden]
  • A. Schlossturm
    Schlossturm is a historic castle tower and prominent architectural landmark located on the Rhine riverfront in Düsseldorf’s Old Town.
  • B. Blockhaus
    Blockhaus is a notoriously steep and decisive mountain in Italy’s Apennines, frequently used as a summit finish that shapes the general classification in the Giro d’Italia.
  • C. The Burg
    The Burg is a nickname commonly used to refer to the city of Warrensburg, Missouri.
  • D. The Burg
    The Burg is a colloquial nickname for the city of Pittsburg in southeastern Kansas, often used by locals and students of Pittsburg State University.
  • E. Blok
    Blok is a Russian surname most famously borne by the Symbolist poet Alexander Blok.
  • 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: Blockhusudden
Triple: [Royal Djurgården park, hasLandmark, Blockhusudden]
Generated description
Blockhusudden is a scenic headland and residential area on the eastern tip of Djurgården in Stockholm, known for its waterfront views, historic buildings, and maritime traffic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Blockhusudden
Target entity description: Blockhusudden is a scenic headland and residential area on the eastern tip of Djurgården in Stockholm, known for its waterfront views, historic buildings, and maritime traffic.
  • A. Schlossturm
    Schlossturm is a historic castle tower and prominent architectural landmark located on the Rhine riverfront in Düsseldorf’s Old Town.
  • B. Blockhaus
    Blockhaus is a notoriously steep and decisive mountain in Italy’s Apennines, frequently used as a summit finish that shapes the general classification in the Giro d’Italia.
  • C. The Burg
    The Burg is a nickname commonly used to refer to the city of Warrensburg, Missouri.
  • D. The Burg
    The Burg is a colloquial nickname for the city of Pittsburg in southeastern Kansas, often used by locals and students of Pittsburg State University.
  • E. Blok
    Blok is a Russian surname most famously borne by the Symbolist poet Alexander Blok.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded82e79a481908ddb9609af8c4407 completed April 15, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9de388508190bb0ecc04740cbe15 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9f2b71808190b961193ae1ddebf0 completed May 9, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_69fe9fa89bd481909235d2ec377a0d8e completed May 9, 2026, 2:44 a.m.
Created at: April 10, 2026, 3 a.m.