Triple

T20378532
Position Surface form Disambiguated ID Type / Status
Subject Paris-Austerlitz E497755 entity
Predicate connectsTo P845 FINISHED
Object Limoges 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: Limoges | Statement: [Paris-Austerlitz, connectsTo, Limoges]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Limoges
Context triple: [Paris-Austerlitz, connectsTo, Limoges]
  • A. Limoges chosen
    Limoges is a historic city in central France renowned for its fine porcelain production and medieval architecture.
  • B. Limoges
    Limoges is a small rural community located within Russell County in eastern Ontario, Canada, known for its proximity to Ottawa and nearby recreational areas.
  • C. Aubusson
    Aubusson is a town in central France renowned for its centuries-old tradition of tapestry and carpet weaving.
  • D. Desnos
    Desnos is the surname of Robert Desnos, a notable French surrealist poet and member of the Resistance during World War II.
  • E. Lubersac
    Lubersac is a small commune in the Corrèze department of south-central France, known for its rural character and traditional Limousin heritage.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678af651c8190b4922294a937e699 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.