Triple

T15261018
Position Surface form Disambiguated ID Type / Status
Subject Kauto Star E364773 entity
Predicate grandsire P979 FINISHED
Object Moulin
Moulin was a Thoroughbred racehorse known primarily as an ancestor in the pedigree of the champion steeplechaser Kauto Star.
E1146578 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: Moulin | Statement: [Kauto Star, grandsire, Moulin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moulin
Context triple: [Kauto Star, grandsire, Moulin]
  • A. Moulin
    Moulin is a French commune known for its cultural and municipal partnership as a twin town of Wesel, Germany.
  • B. Moulin
    Moulin is a French surname most famously associated with Jean Moulin, a leading figure of the French Resistance during World War II.
  • C. Moulin-à-Vent
    Moulin-à-Vent is a renowned French appellation in the Beaujolais region known for producing some of its most structured, age-worthy red wines, primarily from the Gamay grape.
  • D. Moulins
    Moulins is a historic town in central France known for its well-preserved medieval architecture and cultural heritage.
  • E. Moulin de Sannois
    Moulin de Sannois is a historic windmill in the town of Sannois, France, known as a prominent local heritage site and viewpoint.
  • 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: Moulin
Triple: [Kauto Star, grandsire, Moulin]
Generated description
Moulin was a Thoroughbred racehorse known primarily as an ancestor in the pedigree of the champion steeplechaser Kauto Star.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Moulin
Target entity description: Moulin was a Thoroughbred racehorse known primarily as an ancestor in the pedigree of the champion steeplechaser Kauto Star.
  • A. Moulin
    Moulin is a French commune known for its cultural and municipal partnership as a twin town of Wesel, Germany.
  • B. Moulin
    Moulin is a French surname most famously associated with Jean Moulin, a leading figure of the French Resistance during World War II.
  • C. Moulin-à-Vent
    Moulin-à-Vent is a renowned French appellation in the Beaujolais region known for producing some of its most structured, age-worthy red wines, primarily from the Gamay grape.
  • D. Moulins
    Moulins is a historic town in central France known for its well-preserved medieval architecture and cultural heritage.
  • E. Moulin de Sannois
    Moulin de Sannois is a historic windmill in the town of Sannois, France, known as a prominent local heritage site and viewpoint.
  • 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_69d85a0f08408190b3c3259ae35d79d2 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0084e85a08190b8e63598b9f6a535 completed April 15, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fee5fb8b30819096d31ba5884715c9 completed May 9, 2026, 7:44 a.m.
NEDg Description generation batch_69fee805f5bc8190a6095e3c374f3441 completed May 9, 2026, 7:53 a.m.
NED2 Entity disambiguation (via description) batch_69fee8e4dc688190bd597f8d710c8afc completed May 9, 2026, 7:57 a.m.
Created at: April 10, 2026, 3:14 a.m.