Triple

T4841043
Position Surface form Disambiguated ID Type / Status
Subject Roscoff E108179 entity
Predicate hasPart P35 FINISHED
Object Roscoff ferry terminal E474293 NE 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: Roscoff ferry terminal | Statement: [Roscoff, hasPart, Roscoff ferry terminal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roscoff ferry terminal
Context triple: [Roscoff, hasPart, Roscoff ferry terminal]
  • A. Port of Roscoff chosen
    The Port of Roscoff is a ferry and commercial harbor in Brittany, France, serving as a key maritime link between France, the United Kingdom, and Ireland.
  • B. Port of Boulogne-sur-Mer
    The Port of Boulogne-sur-Mer is a major French fishing and commercial harbor on the English Channel, known as one of Europe’s leading seafood ports.
  • C. Port of Rouen
    The Port of Rouen is a major French inland seaport and grain-export hub located on the River Seine between Paris and the English Channel.
  • D. Port of Le Havre
    The Port of Le Havre is one of France’s largest and busiest seaports, serving as a major gateway for maritime trade on the English Channel and the North Sea.
  • E. Roscoff, France
    Roscoff, France is a small coastal town in Brittany known for its historic port, thalassotherapy centers, and traditional onion-growing heritage.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4409b264819085ab855f3eb5381a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6cfbfbb08190b4580ebb2eb845b2 completed March 20, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69be67d449188190a2f02fa30aee4891 completed March 21, 2026, 9:41 a.m.
Created at: March 20, 2026, 1:25 p.m.