Triple

T749528
Position Surface form Disambiguated ID Type / Status
Subject Heidelberg E15415 entity
Predicate hasLandmark P105 FINISHED
Object Königstuhl
Königstuhl is a prominent hill overlooking Heidelberg in southwestern Germany, known for its panoramic views, observatories, and access via a historic funicular railway.
E93752 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: Königstuhl | Statement: [Heidelberg, hasLandmark, Königstuhl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Königstuhl
Context triple: [Heidelberg, hasLandmark, Königstuhl]
  • A. Brocken
    Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
  • B. Erzhausen
    Erzhausen is a small municipality in the state of Hesse in central Germany, located near Darmstadt and part of the Rhine-Main metropolitan region.
  • C. Feldberg
    Feldberg is the tallest mountain in Germany’s Black Forest region, known for its scenic landscapes and popular hiking and skiing opportunities.
  • D. Zumsteinspitze
    Zumsteinspitze is one of the high summits of the Monte Rosa massif in the Pennine Alps on the border between Switzerland and Italy.
  • E. Hallbergmoos
    Hallbergmoos is a municipality in Bavaria, Germany, known for hosting major aerospace and technology companies near Munich.
  • 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: Königstuhl
Triple: [Heidelberg, hasLandmark, Königstuhl]
Generated description
Königstuhl is a prominent hill overlooking Heidelberg in southwestern Germany, known for its panoramic views, observatories, and access via a historic funicular railway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Königstuhl
Target entity description: Königstuhl is a prominent hill overlooking Heidelberg in southwestern Germany, known for its panoramic views, observatories, and access via a historic funicular railway.
  • A. Brocken
    Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
  • B. Erzhausen
    Erzhausen is a small municipality in the state of Hesse in central Germany, located near Darmstadt and part of the Rhine-Main metropolitan region.
  • C. Feldberg
    Feldberg is the tallest mountain in Germany’s Black Forest region, known for its scenic landscapes and popular hiking and skiing opportunities.
  • D. Zumsteinspitze
    Zumsteinspitze is one of the high summits of the Monte Rosa massif in the Pennine Alps on the border between Switzerland and Italy.
  • E. Hallbergmoos
    Hallbergmoos is a municipality in Bavaria, Germany, known for hosting major aerospace and technology companies near Munich.
  • 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_69a493599a0081908da65f3407af1ef2 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a6304e0c8190827fb57c5cac2da9 completed March 1, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69a67878516c8190ac7682239dc63b6a completed March 3, 2026, 5:58 a.m.
NEDg Description generation batch_69a679738e508190a9fec24f2490f46b completed March 3, 2026, 6:02 a.m.
NED2 Entity disambiguation (via description) batch_69a679c1a8748190a1da4a4f1bfc417f completed March 3, 2026, 6:03 a.m.
Created at: March 1, 2026, 7:37 p.m.