Triple

T16490682
Position Surface form Disambiguated ID Type / Status
Subject Landstinget E400558 entity
Predicate seeAlso P37 FINISHED
Object Inatsisartut E88947 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: Inatsisartut | Statement: [Landstinget, seeAlso, Inatsisartut]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Inatsisartut
Context triple: [Landstinget, seeAlso, Inatsisartut]
  • A. Inatsisartut chosen
    Inatsisartut is the unicameral parliament of Greenland, responsible for making laws and overseeing the autonomous territory’s government.
  • B. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • C. Tori’untu
    Tori’untu is a regional dialect of the Uma language spoken by a subset of Uma-speaking communities.
  • D. Makeatutara
    Makeatutara is a figure in Māori mythology known as the father of the demigod Māui and a guardian associated with the underworld.
  • E. Sitaantaagu
    Sitaantaagu is the Tlingit name for the Mendenhall Glacier near Juneau, Alaska, a prominent valley glacier and major natural landmark.
  • 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_69d883813098819084f5409539723b59 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e2f31f48190825af5934d976ab7 completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a007d9e91f48190b83cefdd2b518082 completed May 10, 2026, 12:44 p.m.
Created at: April 10, 2026, 5:13 a.m.