Triple

T10770831
Position Surface form Disambiguated ID Type / Status
Subject Mabillon E254069 entity
Predicate municipality P852 FINISHED
Object Paris
Paris is the capital and largest city of France, renowned for its historic architecture, cultural institutions, fashion, and cuisine.
 E568 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: Paris | Statement: [Mabillon, municipality, Paris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Paris
Context triple: [Mabillon, municipality, Paris]
  • A. Paris
    Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
  • B. Paris
    Paris is a prince of Troy in Greek mythology, best known for judging the beauty contest of the goddesses and for abducting Helen, which sparked the Trojan War.
  • C. Paris
    Paris is a major Chilean department store and retail chain offering a wide range of apparel, home goods, and consumer products.
  • D. Paris
    Paris is a budget-oriented AMD Sempron processor core designed for entry-level desktop computing.
  • E. Parigi
    Parigi is a coastal town that serves as the administrative center of Parigi Moutong Regency in Central Sulawesi, Indonesia.
  • 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: Paris
Triple: [Mabillon, municipality, Paris]
Generated description
Paris is the capital and largest city of France, renowned for its historic architecture, cultural institutions, fashion, and cuisine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Paris
Target entity description: Paris is the capital and largest city of France, renowned for its historic architecture, cultural institutions, fashion, and cuisine.
  • A. Paris chosen
    Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
  • B. Paris
    Paris is a prince of Troy in Greek mythology, best known for judging the beauty contest of the goddesses and for abducting Helen, which sparked the Trojan War.
  • C. Paris
    Paris is a major Chilean department store and retail chain offering a wide range of apparel, home goods, and consumer products.
  • D. Paris
    Paris is a budget-oriented AMD Sempron processor core designed for entry-level desktop computing.
  • E. Parigi
    Parigi is a coastal town that serves as the administrative center of Parigi Moutong Regency in Central Sulawesi, Indonesia.
  • F. None of above.

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_69d6aa5f54f4819082d0bbcb6f8797e6 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d732314bcc8190980c6f698f64ccf5 completed April 9, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69de2297f7a48190b194f7e611d0682b completed April 14, 2026, 11:18 a.m.
NEDg Description generation batch_69de25d50e40819089740d725c054321 completed April 14, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_69de280e5a588190be23778041249456 completed April 14, 2026, 11:42 a.m.
Created at: April 8, 2026, 9:16 p.m.