Triple

T11534683
Position Surface form Disambiguated ID Type / Status
Subject Trois-Ponts E273515 entity
Predicate crossedByRiver P225 FINISHED
Object Salm
The Salm is a river in eastern Belgium that flows through the Ardennes region, including the town of Trois-Ponts.
 E931289 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: Salm | Statement: [Trois-Ponts, crossedByRiver, Salm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Salm
Context triple: [Trois-Ponts, crossedByRiver, Salm]
  • A. Sulmo
    Sulmo is an ancient town in central Italy, historically known as the birthplace of the Roman poet Ovid.
  • B. Salamansa
    Salamansa is a coastal village on the island of São Vicente in Cape Verde, known for its fishing community and sandy beach.
  • C. Surmali
    Surmali was a historic town in the South Caucasus region, known as the administrative center of the Surmalu uezd in the Russian Empire and later part of present-day Turkey.
  • D. Salme
    Salme is a small village and former rural municipality located on Saaremaa Island in western Estonia.
  • E. Sutsilvan
    Sutsilvan is a traditional variety of the Romansh language historically spoken in parts of the Swiss canton of Graubünden.
  • 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: Salm
Triple: [Trois-Ponts, crossedByRiver, Salm]
Generated description
The Salm is a river in eastern Belgium that flows through the Ardennes region, including the town of Trois-Ponts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Salm
Target entity description: The Salm is a river in eastern Belgium that flows through the Ardennes region, including the town of Trois-Ponts.
  • A. Sulmo
    Sulmo is an ancient town in central Italy, historically known as the birthplace of the Roman poet Ovid.
  • B. Salamansa
    Salamansa is a coastal village on the island of São Vicente in Cape Verde, known for its fishing community and sandy beach.
  • C. Surmali
    Surmali was a historic town in the South Caucasus region, known as the administrative center of the Surmalu uezd in the Russian Empire and later part of present-day Turkey.
  • D. Salme
    Salme is a small village and former rural municipality located on Saaremaa Island in western Estonia.
  • E. Sutsilvan
    Sutsilvan is a traditional variety of the Romansh language historically spoken in parts of the Swiss canton of Graubünden.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8839b4bb48190b748ec4119f36c11 completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6858af0d081909078d5862ec3d469 completed April 20, 2026, 7:59 p.m.
NEDg Description generation batch_69e68fd8210c8190a7b0bbd8a50ff6b1 completed April 20, 2026, 8:43 p.m.
NED2 Entity disambiguation (via description) batch_69e69f12cfcc8190a06e0922c9faa49e completed April 20, 2026, 9:48 p.m.
Created at: April 8, 2026, 9:37 p.m.