Triple

T2781238
Position Surface form Disambiguated ID Type / Status
Subject Historisches Museum Frankfurt E61698 entity
Predicate hasBuildingPart P35 FINISHED
Object Saalhof
Saalhof is a historic medieval building complex in Frankfurt am Main that forms part of the city’s museum landscape and reflects its architectural and urban history.
E301852 NE FINISHED

How this triple was built (5 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: Saalhof | Statement: [Historisches Museum Frankfurt, hasBuildingPart, Saalhof]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saalhof
Context triple: [Historisches Museum Frankfurt, hasBuildingPart, Saalhof]
  • A. Selhof
    Selhof is a district of the German town of Bad Honnef in the state of North Rhine-Westphalia.
  • B. Schöngarth
    Schöngarth is a German surname most notably associated with Eberhard Schöngarth, a high-ranking Nazi SS officer and war criminal during World War II.
  • C. Reundorf
    Reundorf is a village-level subdivision of the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • D. Schaafheim
    Schaafheim is a municipality in the state of Hesse in central Germany.
  • E. Heidenfeld
    Heidenfeld is a village in Bavaria, Germany, known as the birthplace of Cardinal Michael von Faulhaber.
  • 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: Saalhof
Triple: [Historisches Museum Frankfurt, hasBuildingPart, Saalhof]
Generated description
Saalhof is a historic medieval building complex in Frankfurt am Main that forms part of the city’s museum landscape and reflects its architectural and urban history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saalhof
Target entity description: Saalhof is a historic medieval building complex in Frankfurt am Main that forms part of the city’s museum landscape and reflects its architectural and urban history.
  • A. Selhof
    Selhof is a district of the German town of Bad Honnef in the state of North Rhine-Westphalia.
  • B. Schöngarth
    Schöngarth is a German surname most notably associated with Eberhard Schöngarth, a high-ranking Nazi SS officer and war criminal during World War II.
  • C. Reundorf
    Reundorf is a village-level subdivision of the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • D. Schaafheim
    Schaafheim is a municipality in the state of Hesse in central Germany.
  • E. Heidenfeld
    Heidenfeld is a village in Bavaria, Germany, known as the birthplace of Cardinal Michael von Faulhaber.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasBuildingPart
Context triple: [Historisches Museum Frankfurt, hasBuildingPart, Saalhof]
  • A. containsBuilding
    Indicates that one location or area includes a building within its boundaries.
  • B. hasPart chosen
    Indicates that one entity is a component, segment, or constituent part of another entity.
  • C. hasBuildingFunction
    Indicates that a building is used for or serves a particular function or purpose.
  • D. hasStationBuildingMaterial
    Indicates that a station’s building is constructed from, or primarily composed of, a specified material.
  • E. hasPartIn
    Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
  • F. None of above.

Provenance (6 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_69ab4b7e43c48190997b8fc8fb1663ab completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abddceb9d88190961e30d521a21552 completed March 7, 2026, 8:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69afce8c2a088190824c1a720db05382 completed March 10, 2026, 7:55 a.m.
NEDg Description generation batch_69afcf7cc6f08190aefbe07ef51f1928 completed March 10, 2026, 7:59 a.m.
NED2 Entity disambiguation (via description) batch_69afcfd803848190921f73fe1b15a01b completed March 10, 2026, 8:01 a.m.
PD Predicate disambiguation batch_69abdd00b65c8190a8ea444308c4fa2b completed March 7, 2026, 8:08 a.m.
Created at: March 6, 2026, 9:57 p.m.