Triple

T2948987
Position Surface form Disambiguated ID Type / Status
Subject Southern Scotland E79571 entity
Predicate hasSettlement P1068 FINISHED
Object Annan E304722 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: Annan | Statement: [Southern Scotland, hasSettlement, Annan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Annan
Context triple: [Southern Scotland, hasSettlement, Annan]
  • A. Annan
    Annan is the surname of Kofi Annan, the Ghanaian diplomat and former Secretary-General of the United Nations.
  • B. Annan chosen
    Annan is a small coastal town and former royal burgh in Dumfries and Galloway in southwest Scotland, situated near the mouth of the River Annan.
  • C. Annan District
    Annan District is a coastal urban district in Tainan, Taiwan, known for its wetlands, historical sites, and traditional fishing villages.
  • D. Alnôba
    Alnôba is an Indigenous Algonquian language traditionally spoken by the Western Abenaki people of northeastern North America.
  • E. Sodankylä
    Sodankylä is a municipality in Finnish Lapland known for its northern location, Arctic climate research, and the annual Midnight Sun Film Festival.
  • 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_69ad8b1089588190b74d9e2505e45762 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad98b6cab88190b4dee7e5ec9347e5 completed March 8, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0869732d08190bdb6f6c76411ade1 completed March 10, 2026, 9:01 p.m.
Created at: March 8, 2026, 2:57 p.m.