Triple

T3140837
Position Surface form Disambiguated ID Type / Status
Subject Gardens of the Palace of Versailles E65639 entity
Predicate irrigationSystem P8844 FINISHED
Object Machine de Marly (historical water supply system)
The Machine de Marly was a monumental 17th-century hydraulic engineering work on the Seine that used an elaborate system of pumps and waterwheels to lift water to the aqueducts supplying Versailles and Marly-le-Roi.
E332646 NE FINISHED

How this triple was built (5 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: Machine de Marly (historical water supply system) | Statement: [Gardens of the Palace of Versailles, irrigationSystem, Machine de Marly (historical water supply system)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Machine de Marly (historical water supply system)
Context triple: [Gardens of the Palace of Versailles, irrigationSystem, Machine de Marly (historical water supply system)]
  • A. Château d’Eau
    Château d’Eau is a Paris Métro station in the 10th arrondissement, located near Gare de l’Est and serving the bustling Boulevard de Strasbourg area.
  • B. Fontaine-de-Vaucluse
    Fontaine-de-Vaucluse is a picturesque village in southeastern France renowned for its powerful karst spring, one of the largest in the world, and its association with the poet Petrarch.
  • C. Fontaine des Éléphants
    Fontaine des Éléphants is a monumental 19th-century fountain in Chambéry, France, featuring four large sculpted elephants and serving as the city’s most iconic symbol.
  • D. Pont del Diable aqueduct
    The Pont del Diable aqueduct is an ancient Roman bridge-aqueduct near Tarragona, Spain, renowned for its well-preserved arches and role in supplying water to the historic city.
  • E. Château de Marly
    Château de Marly was a lavish 17th-century royal retreat near Versailles, built for Louis XIV as an intimate pleasure residence distinct from the main court.
  • 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: Machine de Marly (historical water supply system)
Triple: [Gardens of the Palace of Versailles, irrigationSystem, Machine de Marly (historical water supply system)]
Generated description
The Machine de Marly was a monumental 17th-century hydraulic engineering work on the Seine that used an elaborate system of pumps and waterwheels to lift water to the aqueducts supplying Versailles and Marly-le-Roi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Machine de Marly (historical water supply system)
Target entity description: The Machine de Marly was a monumental 17th-century hydraulic engineering work on the Seine that used an elaborate system of pumps and waterwheels to lift water to the aqueducts supplying Versailles and Marly-le-Roi.
  • A. Château d’Eau
    Château d’Eau is a Paris Métro station in the 10th arrondissement, located near Gare de l’Est and serving the bustling Boulevard de Strasbourg area.
  • B. Fontaine-de-Vaucluse
    Fontaine-de-Vaucluse is a picturesque village in southeastern France renowned for its powerful karst spring, one of the largest in the world, and its association with the poet Petrarch.
  • C. Fontaine des Éléphants
    Fontaine des Éléphants is a monumental 19th-century fountain in Chambéry, France, featuring four large sculpted elephants and serving as the city’s most iconic symbol.
  • D. Pont del Diable aqueduct
    The Pont del Diable aqueduct is an ancient Roman bridge-aqueduct near Tarragona, Spain, renowned for its well-preserved arches and role in supplying water to the historic city.
  • E. Château de Marly
    Château de Marly was a lavish 17th-century royal retreat near Versailles, built for Louis XIV as an intimate pleasure residence distinct from the main court.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: irrigationSystem
Context triple: [Gardens of the Palace of Versailles, irrigationSystem, Machine de Marly (historical water supply system)]
  • A. hasIrrigation
    Indicates that an entity is equipped with or benefits from an irrigation system supplying water.
  • B. irrigates chosen
    Indicates that one entity supplies water to another, typically land or crops, for the purpose of supporting growth or maintaining moisture.
  • C. irrigationProjectIn
    Indicates that an irrigation project is located within or implemented in a specified geographic or administrative area.
  • D. hasIrrigationArea
    Indicates that an entity possesses or is associated with a specific area of land equipped or designated for irrigation.
  • E. nearIrrigationProject
    Indicates that one entity is located close to or in the vicinity of an irrigation project.
  • F. None of above.

Provenance (6 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_69ad8582f564819088c27e1f96153938 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada57895dc8190bd3d4ef9391973dc completed March 8, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69b224e4df38819089d0a11016a85ad8 completed March 12, 2026, 2:28 a.m.
NEDg Description generation batch_69b228c1b568819088dc5ce4a15fedc2 completed March 12, 2026, 2:45 a.m.
NED2 Entity disambiguation (via description) batch_69b22ccd34a8819089e207b6ee1f634a completed March 12, 2026, 3:02 a.m.
PD Predicate disambiguation batch_69ad9df840088190a26a1516f4c1f056 completed March 8, 2026, 4:04 p.m.
Created at: March 8, 2026, 3:05 p.m.