Triple

T16692897
Position Surface form Disambiguated ID Type / Status
Subject Cirque de Navacelles E405636 entity
Predicate river P165 FINISHED
Object Vis
Vis is a river in southern France known for carving the dramatic Cirque de Navacelles canyon through the limestone plateaus of the Cévennes region.
 E1229136 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: Vis | Statement: [Cirque de Navacelles, river, Vis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vis
Context triple: [Cirque de Navacelles, river, Vis]
  • A. Vis
    Vis is a Croatian island in the Adriatic Sea known for its unspoiled nature, historic towns, and former role as a strategic military base.
  • B. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • C. VIS
    VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
  • D. Vin
    Vin is a common shortened form of the given name Vincent, often used as an informal or familiar nickname.
  • E. Vis a vis
    Vis a vis is a Spanish prison drama television series that follows the transformation of a naive young woman after she is incarcerated in a high-security women’s prison.
  • 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: Vis
Triple: [Cirque de Navacelles, river, Vis]
Generated description
Vis is a river in southern France known for carving the dramatic Cirque de Navacelles canyon through the limestone plateaus of the Cévennes region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vis
Target entity description: Vis is a river in southern France known for carving the dramatic Cirque de Navacelles canyon through the limestone plateaus of the Cévennes region.
  • A. Vis
    Vis is a Croatian island in the Adriatic Sea known for its unspoiled nature, historic towns, and former role as a strategic military base.
  • B. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • C. VIS
    VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
  • D. Vin
    Vin is a common shortened form of the given name Vincent, often used as an informal or familiar nickname.
  • E. Vis a vis
    Vis a vis is a Spanish prison drama television series that follows the transformation of a naive young woman after she is incarcerated in a high-security women’s prison.
  • 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_69d8838c28748190b3f5967c743940ab completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37eaacb948190954231c9e97a4adf completed April 18, 2026, 12:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0091984dcc8190b0b20d2e57bc3a11 completed May 10, 2026, 2:09 p.m.
NEDg Description generation batch_6a0092244d788190b24f56f0b166dc20 completed May 10, 2026, 2:11 p.m.
NED2 Entity disambiguation (via description) batch_6a00929d803881908d0bb6c566cd112a completed May 10, 2026, 2:13 p.m.
Created at: April 10, 2026, 5:19 a.m.