Triple

T16522754
Position Surface form Disambiguated ID Type / Status
Subject Paradiso E401358 entity
Predicate borders P224 FINISHED
Object Melide E89716 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: Melide | Statement: [Paradiso, borders, Melide]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Melide
Context triple: [Paradiso, borders, Melide]
  • A. Melide chosen
    Melide is a Swiss municipality in the canton of Ticino, known for its scenic location on Lake Lugano and the Swissminiatur open-air miniature park.
  • B. Meride
    Meride is a small village in the canton of Ticino in southern Switzerland, known for its scenic location on Monte San Giorgio, a UNESCO World Heritage site famed for its fossil-rich geological formations.
  • C. Melsisi
    Melsisi is a coastal village and mission station on Pentecost Island in Vanuatu, known for its Catholic mission, school, and local health services.
  • D. Artouz
    Artouz is a town in southwestern Syria located near Damascus within the Rif Dimashq region.
  • E. Staouéli
    Staouéli is a coastal town in northern Algeria, near Algiers, known historically as the site of a major 1830 battle during the French conquest of Algeria.
  • 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e8158cc8190aa77c6d37bd7ec76 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00608b7f6081909912dd575979f8d7 completed May 10, 2026, 10:40 a.m.
Created at: April 10, 2026, 5:14 a.m.