Triple

T11017359
Position Surface form Disambiguated ID Type / Status
Subject Hæren E260396 entity
Predicate garrison P75 FINISHED
Object Setermoen E381848 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: Setermoen | Statement: [Hæren, garrison, Setermoen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Setermoen
Context triple: [Hæren, garrison, Setermoen]
  • A. Setermoen chosen
    Setermoen is a small town in northern Norway that serves as the administrative center of Bardu Municipality and hosts one of the country’s main military garrisons.
  • B. The Settlement
    The Settlement is the main inhabited village of Edinburgh of the Seven Seas, the remote capital of Tristan da Cunha in the South Atlantic Ocean.
  • C. Settle
    Settle is a small market town in North Yorkshire, England, known as a gateway to the Yorkshire Dales and the scenic Settle–Carlisle railway.
  • D. Sepetiba
    Sepetiba is a coastal neighborhood in Rio de Janeiro known for its bay, fishing activities, and industrial port area.
  • E. Entemena
    Entemena was an early dynastic Sumerian ruler of the city-state of Lagash, known for consolidating its power and commissioning some of the earliest known royal inscriptions.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797a7f4a881908232f99d18d95149 completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e374d371ec8190aba9e77346c6e876 completed April 18, 2026, 12:10 p.m.
Created at: April 8, 2026, 9:25 p.m.