Triple

T21123101
Position Surface form Disambiguated ID Type / Status
Subject Kras E520481 entity
Predicate hasSettlement P1068 FINISHED
Object Komen 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: Komen | Statement: [Kras, hasSettlement, Komen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Komen
Context triple: [Kras, hasSettlement, Komen]
  • A. Komen
    Komen is the surname associated with Susan G. Komen, whose name is borne by a major U.S. breast cancer advocacy and research organization.
  • B. Komen chosen
    Komen is a municipality in western Slovenia’s Littoral region, known for its karst landscape and proximity to the Italian border.
  • C. Corme
    Corme is a coastal village in Galicia, northwestern Spain, known for its fishing heritage and dramatic Atlantic scenery along the Costa da Morte.
  • D. Koules
    Koules is a Venetian-era coastal fortress in Heraklion, Crete, that historically protected the city’s harbor and now serves as a prominent cultural and tourist landmark.
  • E. Komsi
    Komsi is a Finnish surname most notably borne by acclaimed coloratura soprano Anu Komsi.
  • 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_69e0b50a623881909c0bbaf4f2c055e7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72236b2d88190bef9f0cd6924ca92 completed April 21, 2026, 7:07 a.m.
Created at: April 16, 2026, 2:55 p.m.