Triple

T19247923
Position Surface form Disambiguated ID Type / Status
Subject Cambrai railway station E481311 entity
Predicate connectsTo P845 FINISHED
Object Somain NE NERFINISHED

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: Somain | Statement: [Cambrai railway station, connectsTo, Somain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somain
Context triple: [Cambrai railway station, connectsTo, Somain]
  • A. Somain chosen
    Somain is a commune in northern France’s Nord department, situated within the industrial and mining basin near Douai.
  • B. St Clement Danes
    St Clement Danes is a historic Church of England building on the Strand in central London, best known as the central church of the Royal Air Force.
  • C. Syon House
    Syon House is a historic stately home in west London, renowned as the London residence of the Duke of Northumberland and noted for its grand architecture and landscaped gardens.
  • D. Saint-Spire Collegiate Church
    Saint-Spire Collegiate Church is a historic Roman Catholic church in Corbeil-Essonnes, France, notable for its medieval architecture and status as a co-cathedral of the local diocese.
  • E. Clerecía Church
    Clerecía Church is a grand Baroque Jesuit church and college complex in Salamanca, Spain, noted for its imposing façade and prominent twin towers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb2e7cf881908dafd45d7a305c52 completed April 20, 2026, 10:08 a.m.
Created at: April 10, 2026, 1:27 p.m.