Triple

T19816968
Position Surface form Disambiguated ID Type / Status
Subject Marquess of Ailsa E476082 entity
Predicate territorialDesignation P14731 FINISHED
Object Ailsa NE NERFINISHED

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: Ailsa | Statement: [Marquess of Ailsa, territorialDesignation, Ailsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ailsa
Context triple: [Marquess of Ailsa, territorialDesignation, Ailsa]
  • A. Ailsa chosen
    Ailsa is a feminine given name of Scottish origin, often associated with the island of Ailsa Craig and used in English-speaking countries.
  • B. Ailsa Course
    Ailsa Course is a renowned championship golf course at the Trump Turnberry resort in Scotland, famous for hosting multiple Open Championships and its dramatic coastal setting overlooking Ailsa Craig.
  • C. Bonawe
    Bonawe is a small settlement in Argyll and Bute, western Scotland, known for its scenic Highland setting and historic ironworks.
  • D. Morvern
    Morvern is a remote peninsula on the west coast of the Scottish Highlands, known for its rugged landscapes, sparse population, and historic ties to Highland clans.
  • E. Lyndall
    Lyndall is a given name that can be used for people of any gender, often considered a variant or related form of the name Lyndon.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e654f9c5b08190987237f5144c3b37 completed April 20, 2026, 4:31 p.m.
Created at: April 10, 2026, 1:50 p.m.