Triple

T16140417
Position Surface form Disambiguated ID Type / Status
Subject Conca E391637 entity
Predicate trailTerminusOf P388 FINISHED
Object GR20 E391634 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: GR20 | Statement: [Conca, trailTerminusOf, GR20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GR20
Context triple: [Conca, trailTerminusOf, GR20]
  • A. GR 20 chosen
    GR 20 is a renowned long-distance hiking trail in Corsica, France, considered one of the toughest and most spectacular treks in Europe.
  • B. GR 34
    GR 34 is a long-distance coastal hiking trail in France that follows much of the Brittany shoreline, offering scenic seaside routes and cultural landmarks.
  • C. GR70
    GR70 is a long-distance hiking trail in France, famously following the route taken by writer Robert Louis Stevenson through the Cévennes region.
  • D. GR-42
    GR-42 is the ISO 3166-2 subdivision code assigned to the Larissa regional unit in Greece.
  • E. GR 36
    GR 36 is a long-distance hiking trail in the French GR footpath network, known for crossing varied landscapes and connecting multiple regions.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21a07b7908190b4e1ec57f60a9274 completed April 17, 2026, 11:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7a59c0481908eb346efaf10a0f6 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:01 a.m.