Triple

T6426030
Position Surface form Disambiguated ID Type / Status
Subject Trondheimsfjord E128059 entity
Predicate drainedByRiver P4497 FINISHED
Object Orkla E470025 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: Orkla | Statement: [Trondheimsfjord, drainedByRiver, Orkla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orkla
Context triple: [Trondheimsfjord, drainedByRiver, Orkla]
  • A. Orkla chosen
    Orkla is a major river in Trøndelag county, Norway, known for its scenic valley and renowned salmon fishing.
  • B. Borregaard
    Borregaard is a Norwegian biorefinery company that produces advanced and sustainable bio-based chemicals and materials from wood.
  • C. Aker Finnyards
    Aker Finnyards is a Finnish shipbuilding company known for constructing various naval and commercial vessels, including advanced military ships.
  • D. Invermark
    Invermark is a small settlement in the remote upper reaches of Glen Esk in Angus, Scotland, known as a gateway to surrounding hills and historic estates.
  • E. Aker
    Aker is a historical area and former municipality that once surrounded and included much of what is now Oslo, Norway.
  • 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_69c00838de888190af2eec0b80495efa completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0691f944c81909d4e5d8ef9e494b6 completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640e339108190bbb74c688de574cc completed March 27, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:43 p.m.