Triple

T3356195
Position Surface form Disambiguated ID Type / Status
Subject Kunstmuseum Basel E70609 entity
Predicate locatedOn P40 FINISHED
Object St. Alban-Graben
St. Alban-Graben is a central street in Basel, Switzerland, known for hosting major cultural institutions and serving as an important urban thoroughfare.
 E350828 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: St. Alban-Graben | Statement: [Kunstmuseum Basel, locatedOn, St. Alban-Graben]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: St. Alban-Graben
Context triple: [Kunstmuseum Basel, locatedOn, St. Alban-Graben]
  • A. Kreuzlinger Forstgraben
    Kreuzlinger Forstgraben is a small watercourse in Bavaria that serves as one of the tributary streams feeding into Lake Starnberg.
  • B. Seestraße
    Seestraße is a Berlin U-Bahn station on the U6 line located in the Wedding district of the city.
  • C. Währing
    Währing is a residential district in Vienna, Austria, known for its historic cemeteries, green spaces, and late 19th-century urban architecture.
  • D. Saalgasse
    Saalgasse is a historic street in Frankfurt’s old town, notable for its postwar modernist townhouses built on medieval foundations.
  • E. Burgplatz
    Burgplatz is a historic central square in Braunschweig, Germany, known for its medieval architecture and prominent landmarks such as Dankwarderode Castle and the Brunswick Lion.
  • 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: St. Alban-Graben
Triple: [Kunstmuseum Basel, locatedOn, St. Alban-Graben]
Generated description
St. Alban-Graben is a central street in Basel, Switzerland, known for hosting major cultural institutions and serving as an important urban thoroughfare.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: St. Alban-Graben
Target entity description: St. Alban-Graben is a central street in Basel, Switzerland, known for hosting major cultural institutions and serving as an important urban thoroughfare.
  • A. Kreuzlinger Forstgraben
    Kreuzlinger Forstgraben is a small watercourse in Bavaria that serves as one of the tributary streams feeding into Lake Starnberg.
  • B. Seestraße
    Seestraße is a Berlin U-Bahn station on the U6 line located in the Wedding district of the city.
  • C. Währing
    Währing is a residential district in Vienna, Austria, known for its historic cemeteries, green spaces, and late 19th-century urban architecture.
  • D. Saalgasse
    Saalgasse is a historic street in Frankfurt’s old town, notable for its postwar modernist townhouses built on medieval foundations.
  • E. Burgplatz
    Burgplatz is a historic central square in Braunschweig, Germany, known for its medieval architecture and prominent landmarks such as Dankwarderode Castle and the Brunswick Lion.
  • 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb242d4988190bbac993df587936d completed March 8, 2026, 5:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3253b03e8819082a5bf5bd5c5d5cb completed March 12, 2026, 8:42 p.m.
NEDg Description generation batch_69b325ffdef081909b9665468f305336 completed March 12, 2026, 8:45 p.m.
NED2 Entity disambiguation (via description) batch_69b32714d57c8190a59619dfab19656f completed March 12, 2026, 8:50 p.m.
Created at: March 8, 2026, 3:13 p.m.