Triple

T17809417
Position Surface form Disambiguated ID Type / Status
Subject Mljet National Park E444657 entity
Predicate contains P35 FINISHED
Object Govedjari E1288842 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: Govedjari | Statement: [Mljet National Park, contains, Govedjari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Govedjari
Context triple: [Mljet National Park, contains, Govedjari]
  • A. Govedari chosen
    Govedari is a small village on the Croatian island of Mljet, known for its proximity to Mljet National Park and its tranquil, rural setting.
  • B. Goranci
    Goranci is an alternative name for the Avromani people, a small ethnic group traditionally inhabiting parts of the Balkans.
  • C. Govedartsi
    Govedartsi is a mountain village in southwestern Bulgaria, known as a base for hiking and skiing in the Rila Mountains.
  • D. Djugu
    Djugu is a town and administrative center in northeastern Democratic Republic of the Congo, located within the conflict-affected Ituri region.
  • E. Vandjala
    Vandjala is a small village in northern Estonia located within Harku Parish in Harju County.
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4887976e48190842840ef064dc772 completed April 19, 2026, 7:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02ff5e7d7881908bf08022930edbc1 completed May 12, 2026, 10:22 a.m.
Created at: April 10, 2026, 10:14 a.m.