Triple

T7473198
Position Surface form Disambiguated ID Type / Status
Subject Annandale, Scotland E176559 entity
Predicate containsSettlement P847 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: [Annandale, Scotland, containsSettlement, Annan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Annan
Context triple: [Annandale, Scotland, containsSettlement, 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. Nayki
    Nayki is an island located within Lake Rakshastal in the Tibet Autonomous Region of China.
  • E. Alnôba
    Alnôba is an Indigenous Algonquian language traditionally spoken by the Western Abenaki people of northeastern North America.
  • 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f416d018819098275cc51d8def3f completed March 27, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83480a40c8190a7ae3e08022735a1 completed March 28, 2026, 8:05 p.m.
Created at: March 27, 2026, 3:41 p.m.