Triple

T20137631
Position Surface form Disambiguated ID Type / Status
Subject Harju maakond E491063 entity
Predicate contains P35 FINISHED
Object Anija Parish 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: Anija Parish | Statement: [Harju maakond, contains, Anija Parish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anija Parish
Context triple: [Harju maakond, contains, Anija Parish]
  • A. Anija Parish chosen
    Anija Parish is a rural municipality in northern Estonia known for its forests, rivers, and small settlements within Harju County.
  • B. Saku Parish
    Saku Parish is a rural municipality in northern Estonia known for its proximity to Tallinn and its mix of small-town communities, forests, and agricultural areas.
  • C. Kuusalu Parish
    Kuusalu Parish is a rural municipality in northern Estonia known for its coastal landscapes, forests, and cultural heritage within Harju County.
  • D. Türi Parish
    Türi Parish is a rural municipality in central Estonia known for its small towns, agricultural landscapes, and historic manors.
  • E. Muhu Parish
    Muhu Parish is a rural municipality in Saare County, Estonia, encompassing Muhu Island and several smaller surrounding islets.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6676879f48190a59da04393d2a8cc completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:32 p.m.