Triple

T6375368
Position Surface form Disambiguated ID Type / Status
Subject French Flanders E143452 entity
Predicate contains P35 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: [French Flanders, contains, Gravelines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gravelines
Context triple: [French Flanders, contains, 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. 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.
  • C. 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.
  • D. Calais
    Calais is a major French port city on the northern coast, serving as one of the primary crossing points between France and England.
  • E. Calais
    Calais is a figure from Greek mythology, one of the winged sons of Boreas who joined Jason and the Argonauts on their legendary voyage.
  • 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_69c008d9f4348190ab598a2913259a1c completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0683ab8e08190ab3c9a5000b1d2be completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c638724d448190a7f13a7c449341db completed March 27, 2026, 7:57 a.m.
Created at: March 22, 2026, 4:33 p.m.