Triple

T28829933
Position Surface form Disambiguated ID Type / Status
Subject Canal de Berry E728016 entity
Predicate hasSectionAbandoned P72240 FINISHED
Object Montluçon–Saint-Amand-Montrond section
The Montluçon–Saint-Amand-Montrond section is a disused stretch of the historic Canal de Berry in central France that once linked the towns of Montluçon and Saint-Amand-Montrond for inland water transport.
 E1836876 NE FINISHED

How this triple was built (3 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: Montluçon–Saint-Amand-Montrond section | Statement: [Canal de Berry, hasSectionAbandoned, Montluçon–Saint-Amand-Montrond section]
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: Montluçon–Saint-Amand-Montrond section
Triple: [Canal de Berry, hasSectionAbandoned, Montluçon–Saint-Amand-Montrond section]
Generated description
The Montluçon–Saint-Amand-Montrond section is a disused stretch of the historic Canal de Berry in central France that once linked the towns of Montluçon and Saint-Amand-Montrond for inland water transport.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasSectionAbandoned
Context triple: [Canal de Berry, hasSectionAbandoned, Montluçon–Saint-Amand-Montrond section]
  • A. abandonedBefore
    Indicates that one entity ceased or gave up on something prior in time to another entity doing so.
  • B. abandonedDuring
    Indicates that one entity ceased support for or deserted another entity in the midst of an ongoing process, event, or period.
  • C. partiallyAbandoned
    Indicates that an entity has been abandoned to some extent, but still retains partial use, occupancy, or maintenance.
  • D. abandonedSegment chosen
    Indicates that a previously used portion of something (such as a route, structure, or system) has been given up and is no longer maintained or in active use.
  • E. abandonedIn
    Indicates that one entity was left behind or deserted in the location or context specified by another entity.
  • 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_69f0319dc6088190bbfaa206d40ed74a completed April 28, 2026, 4:03 a.m.
NER Named-entity recognition batch_69fdd07a34c08190982b8c61c2775cf6 completed May 8, 2026, noon
NED1 Entity disambiguation (via context triple) batch_6a24bbaaa9d881908e611a80cb3d151c completed June 7, 2026, 12:30 a.m.
NEDg Description generation batch_6a24bfb0987c819089a6705bb5282c4e completed June 7, 2026, 12:47 a.m.
NED2 Entity disambiguation (via description) batch_6a24c54a5d648190b33935999d8f5f04 completed June 7, 2026, 1:11 a.m.
PD Predicate disambiguation batch_69fdbd25c7908190b72fca8de7ce503f completed May 8, 2026, 10:38 a.m.
Created at: April 28, 2026, 6:37 a.m.