Triple

T6053719
Position Surface form Disambiguated ID Type / Status
Subject Riehen E134855 entity
Predicate locatedOn P40 FINISHED
Object Wiese River
The Wiese River is a tributary of the Rhine flowing through parts of Germany and Switzerland, including the municipality of Riehen near Basel.
 E575959 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: Wiese River | Statement: [Riehen, locatedOn, Wiese River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wiese River
Context triple: [Riehen, locatedOn, Wiese River]
  • A. Schwabach River
    The Schwabach River is a small river in Bavaria, Germany, that flows through the town of Schwabach before joining the Rednitz River.
  • B. Würm River
    The Würm River is a small river in Bavaria, Germany, known for flowing north from Lake Starnberg through towns such as Gauting and Starnberg before joining the Amper River.
  • C. Saalach River
    The Saalach River is an Alpine river in Austria and Germany that flows through the spa town of Bad Reichenhall before joining the Salzach.
  • D. Lachen River
    The Lachen River is a Himalayan mountain river in the Indian state of Sikkim, known for its glacial origins and role in feeding the Teesta River system.
  • E. Wuhle
    Wuhle is a small river in Berlin, Germany, that flows through the eastern districts before joining the Spree.
  • 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: Wiese River
Triple: [Riehen, locatedOn, Wiese River]
Generated description
The Wiese River is a tributary of the Rhine flowing through parts of Germany and Switzerland, including the municipality of Riehen near Basel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wiese River
Target entity description: The Wiese River is a tributary of the Rhine flowing through parts of Germany and Switzerland, including the municipality of Riehen near Basel.
  • A. Schwabach River
    The Schwabach River is a small river in Bavaria, Germany, that flows through the town of Schwabach before joining the Rednitz River.
  • B. Würm River
    The Würm River is a small river in Bavaria, Germany, known for flowing north from Lake Starnberg through towns such as Gauting and Starnberg before joining the Amper River.
  • C. Saalach River
    The Saalach River is an Alpine river in Austria and Germany that flows through the spa town of Bad Reichenhall before joining the Salzach.
  • D. Lachen River
    The Lachen River is a Himalayan mountain river in the Indian state of Sikkim, known for its glacial origins and role in feeding the Teesta River system.
  • E. Wuhle
    Wuhle is a small river in Berlin, Germany, that flows through the eastern districts before joining the Spree.
  • 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_69c00877b6d4819096b0e163728b73a3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05708fda48190ad3d1860969ebb6a completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16ea1595c8190926a5ed8d230ab4a completed March 23, 2026, 4:47 p.m.
NEDg Description generation batch_69c1c533f43881908d57b75237f3c827 completed March 23, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_69c1c59ef9b0819091b05cd30c07d918 completed March 23, 2026, 10:58 p.m.
Created at: March 22, 2026, 4:09 p.m.