Triple

T17240174
Position Surface form Disambiguated ID Type / Status
Subject Caithness E418470 entity
Predicate traditionalLanguage P6149 FINISHED
Object Norn (historically) E97878 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: Norn (historically) | Statement: [Caithness, traditionalLanguage, Norn (historically)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norn (historically)
Context triple: [Caithness, traditionalLanguage, Norn (historically)]
  • A. Norn chosen
    Norn was an extinct North Germanic language once spoken in the Northern Isles of Scotland, particularly Orkney and Shetland.
  • B. Munin
    Munin is a dialect of the Andi language, a Northeast Caucasian language spoken in Dagestan, Russia.
  • C. NORSE
    NORSE is the stock ticker symbol for Norse Atlantic Airways, a low-cost long-haul airline based in Norway.
  • D. Nethuns
    Nethuns is an Etruscan god primarily associated with water, especially wells and the sea, and is often linked to the later Roman god Neptune.
  • E. Norns
    The Norns are powerful female beings in Norse mythology who control fate by weaving the destinies of gods and humans at the roots of the world tree.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42e1f385c8190ae44e702923b6f66 completed April 19, 2026, 1:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0170f1511c8190b70cb37e713a406a completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:39 a.m.