Triple

T12765571
Position Surface form Disambiguated ID Type / Status
Subject Aqueduct Saint-Clément E305113 entity
Predicate connectsWith P37 FINISHED
Object Saint-Clément spring
Saint-Clément spring is a natural water source in southern France that historically supplied the Aqueduct Saint-Clément and the city of Montpellier.
E1001895 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: Saint-Clément spring | Statement: [Aqueduct Saint-Clément, connectsWith, Saint-Clément spring]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint-Clément spring
Context triple: [Aqueduct Saint-Clément, connectsWith, Saint-Clément spring]
  • A. Tournelle
    Tournelle refers to the historical riverside district and former tower area in Paris that gave its name to the Pont de la Tournelle.
  • B. Rethondes
    Rethondes is a commune in northern France best known as the site where the World War I armistice was signed in 1918.
  • C. Aigues-Mortais
    Aigues-Mortais are the inhabitants of Aigues-Mortes, a historic fortified town in the Occitanie region of southern France.
  • D. Fasquelle
    Fasquelle is a French publishing house known for issuing notable literary and scholarly works.
  • E. Arugot Spring
    Arugot Spring is a popular desert oasis and hiking destination in the Ein Gedi Nature Reserve near the Dead Sea in Israel, known for its waterfalls, pools, and lush vegetation.
  • 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: Saint-Clément spring
Triple: [Aqueduct Saint-Clément, connectsWith, Saint-Clément spring]
Generated description
Saint-Clément spring is a natural water source in southern France that historically supplied the Aqueduct Saint-Clément and the city of Montpellier.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saint-Clément spring
Target entity description: Saint-Clément spring is a natural water source in southern France that historically supplied the Aqueduct Saint-Clément and the city of Montpellier.
  • A. Tournelle
    Tournelle refers to the historical riverside district and former tower area in Paris that gave its name to the Pont de la Tournelle.
  • B. Rethondes
    Rethondes is a commune in northern France best known as the site where the World War I armistice was signed in 1918.
  • C. Aigues-Mortais
    Aigues-Mortais are the inhabitants of Aigues-Mortes, a historic fortified town in the Occitanie region of southern France.
  • D. Fasquelle
    Fasquelle is a French publishing house known for issuing notable literary and scholarly works.
  • E. Arugot Spring
    Arugot Spring is a popular desert oasis and hiking destination in the Ein Gedi Nature Reserve near the Dead Sea in Israel, known for its waterfalls, pools, and lush vegetation.
  • 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_69d7bdf1fcd081909ffb0e0d6fa3a07d completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96df1ef148190af525532fcb0933b completed April 10, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f684f4e1508190a6f023f1d1dc192e completed May 2, 2026, 11:12 p.m.
NEDg Description generation batch_69f6863fada48190afe2ff7896a60094 completed May 2, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69f686bcac94819088782273effbb06a completed May 2, 2026, 11:20 p.m.
Created at: April 9, 2026, 5:28 p.m.