Triple

T5012810
Position Surface form Disambiguated ID Type / Status
Subject Werra E112665 entity
Predicate hasRightTributary P415 FINISHED
Object Hörsel
Hörsel is a river in central Germany that flows through Thuringia and joins the Werra, contributing to the region’s drainage system.
 E487361 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: Hörsel | Statement: [Werra, hasRightTributary, Hörsel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hörsel
Context triple: [Werra, hasRightTributary, Hörsel]
  • A. 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.
  • B. Bernlohe
    Bernlohe is a village-level district that forms part of the town of Roth in Bavaria, Germany.
  • C. Hohne
    Hohne is a village in Lower Saxony, Germany, historically notable for its military garrison and association with British Army units.
  • D. Geiereck
    Geiereck is a mountain station area on the Untersberg massif in the Alps, serving as the upper terminus and viewpoint for the Untersbergbahn cable car.
  • E. Solling
    Solling is a forested low mountain range in Lower Saxony, Germany, known for its extensive woodlands and role as a major part of the Weser Uplands.
  • 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: Hörsel
Triple: [Werra, hasRightTributary, Hörsel]
Generated description
Hörsel is a river in central Germany that flows through Thuringia and joins the Werra, contributing to the region’s drainage system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hörsel
Target entity description: Hörsel is a river in central Germany that flows through Thuringia and joins the Werra, contributing to the region’s drainage system.
  • A. 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.
  • B. Bernlohe
    Bernlohe is a village-level district that forms part of the town of Roth in Bavaria, Germany.
  • C. Hohne
    Hohne is a village in Lower Saxony, Germany, historically notable for its military garrison and association with British Army units.
  • D. Geiereck
    Geiereck is a mountain station area on the Untersberg massif in the Alps, serving as the upper terminus and viewpoint for the Untersbergbahn cable car.
  • E. Solling
    Solling is a forested low mountain range in Lower Saxony, Germany, known for its extensive woodlands and role as a major part of the Weser Uplands.
  • 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_69bd4434acb8819086679dbeccc2fe54 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd730f12a481908a27c15dc73987c6 completed March 20, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9271eccc8190bbe9bdb876b41cb8 completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be9653457c819082c4e4436a940f92 completed March 21, 2026, 1 p.m.
NED2 Entity disambiguation (via description) batch_69be96b861d08190b64145f30b3420b5 completed March 21, 2026, 1:01 p.m.
Created at: March 20, 2026, 1:35 p.m.