Triple

T12677876
Position Surface form Disambiguated ID Type / Status
Subject Landshut E302865 entity
Predicate hasLandmark P105 FINISHED
Object Ländtor
Ländtor is a historic city gate in Landshut, Germany, known as one of the town’s most prominent medieval landmarks.
E996733 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: Ländtor | Statement: [Landshut, hasLandmark, Ländtor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ländtor
Context triple: [Landshut, hasLandmark, Ländtor]
  • A. Harlingerland
    Harlingerland is a historic coastal region in East Frisia in northwestern Germany, known for its North Sea landscape, dike systems, and traditional Frisian culture.
  • B. Töwerland
    Töwerland is the poetic nickname for the North Sea island of Juist, known for its tranquil, car-free environment and natural beauty.
  • C. Orlamünde
    Orlamünde is a small historic town in the German state of Thuringia, situated along the Saale River.
  • D. Dodangaslanda
    Dodangaslanda is a rural town and electoral constituency in the Kurunegala District of Sri Lanka.
  • E. Jorsalle
    Jorsalle is a small village in Nepal’s Khumbu region that serves as a common stopover for trekkers on the route to Everest Base Camp.
  • 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: Ländtor
Triple: [Landshut, hasLandmark, Ländtor]
Generated description
Ländtor is a historic city gate in Landshut, Germany, known as one of the town’s most prominent medieval landmarks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ländtor
Target entity description: Ländtor is a historic city gate in Landshut, Germany, known as one of the town’s most prominent medieval landmarks.
  • A. Harlingerland
    Harlingerland is a historic coastal region in East Frisia in northwestern Germany, known for its North Sea landscape, dike systems, and traditional Frisian culture.
  • B. Töwerland
    Töwerland is the poetic nickname for the North Sea island of Juist, known for its tranquil, car-free environment and natural beauty.
  • C. Orlamünde
    Orlamünde is a small historic town in the German state of Thuringia, situated along the Saale River.
  • D. Dodangaslanda
    Dodangaslanda is a rural town and electoral constituency in the Kurunegala District of Sri Lanka.
  • E. Jorsalle
    Jorsalle is a small village in Nepal’s Khumbu region that serves as a common stopover for trekkers on the route to Everest Base Camp.
  • 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_69d7bdee64a08190801c6d470aefd723 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961b1dff48190923290555ece5d89 completed April 10, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671a341288190822fae2469efea09 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f672ac07908190bd2dfe90d55a13c1 completed May 2, 2026, 9:54 p.m.
NED2 Entity disambiguation (via description) batch_69f67360b530819085d5db2aa0b7513d completed May 2, 2026, 9:57 p.m.
Created at: April 9, 2026, 5:20 p.m.