Triple

T7063919
Position Surface form Disambiguated ID Type / Status
Subject Veurne E164295 entity
Predicate hasTwinTown P919 FINISHED
Object Gravelines E403436 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: Gravelines | Statement: [Veurne, hasTwinTown, Gravelines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gravelines
Context triple: [Veurne, hasTwinTown, Gravelines]
  • A. Gravelines chosen
    Gravelines is a coastal commune in northern France known for its historic fortifications and strategic position along the English Channel.
  • B. Boulogne
    Boulogne is a French football club known for being one of the early professional teams in N’Golo Kanté’s career.
  • C. Aire-sur-la-Lys
    Aire-sur-la-Lys is a historic town in northern France’s Pas-de-Calais department, known for its medieval architecture and strategic location near the Lys River.
  • D. Boulogne-sur-Mer
    Boulogne-sur-Mer is a coastal city and major fishing port in northern France, located on the English Channel in the Pas-de-Calais department.
  • E. Calais
    Calais is a major French port city on the northern coast, serving as one of the primary crossing points between France and England.
  • 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_69c688796c148190adb2f1596f595f22 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e45e80e08190bb1a79a6026d2cd5 completed March 27, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c788ba7af88190aeaf3205255af8ad completed March 28, 2026, 7:52 a.m.
Created at: March 27, 2026, 2:38 p.m.