Triple

T4301128
Position Surface form Disambiguated ID Type / Status
Subject Balma E99837 entity
Predicate locatedOnRiver P165 FINISHED
Object Hers-Mort
The Hers-Mort is a river in southwestern France that flows through the Occitanie region and serves as a tributary of the Ariège River.
E428679 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: Hers-Mort | Statement: [Balma, locatedOnRiver, Hers-Mort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hers-Mort
Context triple: [Balma, locatedOnRiver, Hers-Mort]
  • A. Toten
    Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
  • B. Margeride
    Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
  • C. de Mortemart
    De Mortemart is the noble French family name of Madame de Montespan, a prominent 17th-century courtier and mistress of King Louis XIV.
  • D. Mistinguett
    Mistinguett was a famous French actress and singer of the early 20th century, celebrated as one of Paris’s most iconic music-hall stars.
  • E. Henreid
    Henreid is the surname of Paul Henreid, the Austrian-born actor and director best known for his roles in classic Hollywood films such as "Casablanca" and "Now, Voyager."
  • 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: Hers-Mort
Triple: [Balma, locatedOnRiver, Hers-Mort]
Generated description
The Hers-Mort is a river in southwestern France that flows through the Occitanie region and serves as a tributary of the Ariège River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hers-Mort
Target entity description: The Hers-Mort is a river in southwestern France that flows through the Occitanie region and serves as a tributary of the Ariège River.
  • A. Toten
    Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
  • B. Margeride
    Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
  • C. de Mortemart
    De Mortemart is the noble French family name of Madame de Montespan, a prominent 17th-century courtier and mistress of King Louis XIV.
  • D. Mistinguett
    Mistinguett was a famous French actress and singer of the early 20th century, celebrated as one of Paris’s most iconic music-hall stars.
  • E. Henreid
    Henreid is the surname of Paul Henreid, the Austrian-born actor and director best known for his roles in classic Hollywood films such as "Casablanca" and "Now, Voyager."
  • 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_69b345528ebc8190b5abc7e95094792d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3509fb2b88190a13ab88a5b924052 completed March 12, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5c74d59688190820cef42c4228a3a completed March 14, 2026, 8:38 p.m.
NEDg Description generation batch_69b5c7bd187c8190b79894c864ea5b19 completed March 14, 2026, 8:40 p.m.
NED2 Entity disambiguation (via description) batch_69b5c88035dc8190beacf43974a29c78 completed March 14, 2026, 8:43 p.m.
Created at: March 12, 2026, 11:08 p.m.