Triple

T722097
Position Surface form Disambiguated ID Type / Status
Subject Le Havre E14638 entity
Predicate originalName P65 FINISHED
Object Francisville
Francisville is the historical name by which the French port city of Le Havre was originally known.
 E94696 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: Francisville | Statement: [Le Havre, originalName, Francisville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Francisville
Context triple: [Le Havre, originalName, Francisville]
  • A. Bossier City
    Bossier City is a mid-sized city in northwestern Louisiana, located across the Red River from Shreveport and known as part of a regional economic and casino-gaming hub.
  • B. Shreveport
    Shreveport is a major city in northwestern Louisiana known for its role as a regional commercial, cultural, and transportation hub.
  • C. Orleans
    Orleans is a coastal town on outer Cape Cod in Massachusetts known for its beaches, fishing, and role as a popular summer vacation destination.
  • D. New Orleans
    New Orleans is a historic port city in southeastern Louisiana known for its vibrant jazz music, Creole cuisine, and distinctive French and Spanish-influenced architecture.
  • E. Baton Rouge, Louisiana
    Baton Rouge, Louisiana is the capital city of Louisiana, known for its role as a political, industrial, and cultural center along the Mississippi River.
  • 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: Francisville
Triple: [Le Havre, originalName, Francisville]
Generated description
Francisville is the historical name by which the French port city of Le Havre was originally known.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Francisville
Target entity description: Francisville is the historical name by which the French port city of Le Havre was originally known.
  • A. Bossier City
    Bossier City is a mid-sized city in northwestern Louisiana, located across the Red River from Shreveport and known as part of a regional economic and casino-gaming hub.
  • B. Shreveport
    Shreveport is a major city in northwestern Louisiana known for its role as a regional commercial, cultural, and transportation hub.
  • C. Orleans
    Orleans is a coastal town on outer Cape Cod in Massachusetts known for its beaches, fishing, and role as a popular summer vacation destination.
  • D. New Orleans
    New Orleans is a historic port city in southeastern Louisiana known for its vibrant jazz music, Creole cuisine, and distinctive French and Spanish-influenced architecture.
  • E. Baton Rouge, Louisiana
    Baton Rouge, Louisiana is the capital city of Louisiana, known for its role as a political, industrial, and cultural center along the Mississippi River.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a591124c8190842e7ef18b064198 completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a67ef6179c81908e72e3d03b61cca4 completed March 3, 2026, 6:25 a.m.
NEDg Description generation batch_69a67f90c8b081909720e5498d313889 completed March 3, 2026, 6:28 a.m.
NED2 Entity disambiguation (via description) batch_69a683f1ef3081908265a6fa83da8b87 completed March 3, 2026, 6:47 a.m.
Created at: March 1, 2026, 7:37 p.m.