Triple

T22402226
Position Surface form Disambiguated ID Type / Status
Subject Muhu E553788 entity
Predicate hasStrait P2744 FINISHED
Object Suur Strait 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: Suur Strait | Statement: [Muhu, hasStrait, Suur Strait]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suur Strait
Context triple: [Muhu, hasStrait, Suur Strait]
  • A. Suur Strait chosen
    Suur Strait is a body of water in the Baltic Sea that separates the Estonian islands of Muhu and Saaremaa.
  • B. Washington Strait
    Washington Strait is a body of water near Laurie Island in the South Orkney Islands of Antarctica, forming a marine passage in this remote polar region.
  • C. Lidingö strait
    Lidingö strait is a narrow waterway in the Stockholm area separating the island of Lidingö from the mainland and forming part of the inner Stockholm archipelago.
  • D. Danish straits
    The Danish straits are the series of narrow waterways between the North Sea and the Baltic Sea that form a crucial maritime passage for regional and international shipping.
  • E. Kalmar Strait
    Kalmar Strait is the narrow body of water separating the Swedish island of Öland from the mainland province of Småland in the Baltic Sea.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b4a96c8190838f5dda21c4d853 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.