Triple

T12396521
Position Surface form Disambiguated ID Type / Status
Subject Chantiers de l’Atlantique E296130 entity
Predicate shipyardArea P104722 FINISHED
Object approximately 150 hectares LITERAL FINISHED

How this triple was built (2 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: approximately 150 hectares | Statement: [Chantiers de l’Atlantique, shipyardArea, approximately 150 hectares]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: shipyardArea
Context triple: [Chantiers de l’Atlantique, shipyardArea, approximately 150 hectares]
  • A. shipyard
    Indicates a relationship where a location functions as a facility for building, repairing, or maintaining ships.
  • B. shipyardOperator
    Indicates that one entity operates, manages, or runs the shipyard associated with another entity.
  • C. shipbuildingActivity
    Indicates the activity or process of constructing, assembling, or significantly modifying ships or large watercraft.
  • D. hullConstruction
    Indicates the process or activity of building, assembling, or forming the main body (hull) of a vessel or similar structure.
  • E. shipDraft
    Indicates the depth of a ship’s hull below the waterline, typically representing how deeply the vessel sits in the water.
  • F. None of above. chosen

Provenance (4 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fd33f048190b205fd21dc513f6a completed April 10, 2026, 6:22 p.m.
PD Predicate disambiguation batch_69d93ed256788190b704cad171a4824e completed April 10, 2026, 6:17 p.m.
PDg Predicate description generation batch_69d93fa244148190a960be3ff6f1cf45 completed April 10, 2026, 6:21 p.m.
Created at: April 8, 2026, 9:54 p.m.