Triple

T17212357
Position Surface form Disambiguated ID Type / Status
Subject Beaufort Castle E417761 entity
Predicate near P350 FINISHED
Object Inverness E50911 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: Inverness | Statement: [Beaufort Castle, near, Inverness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Inverness
Context triple: [Beaufort Castle, near, Inverness]
  • A. Inverness chosen
    Inverness is a city in the Scottish Highlands that serves as a major cultural and administrative center for the region.
  • B. Inverness
    Inverness is a small coastal locality within Queensland’s Capricorn Coast region in Australia.
  • C. Inverness
    Inverness is a small coastal community in Marin County, California, known for its scenic setting along Tomales Bay near Point Reyes National Seashore.
  • D. Nairn
    Nairn is a coastal town in the Highland council area of Scotland, known as a seaside resort on the Moray Firth.
  • E. Inveraray
    Inveraray is a historic town on the shores of Loch Fyne in western Scotland, noted for Inveraray Castle and its role as the traditional seat of the Dukes of Argyll.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dc68a2c81908564231853b40db9 completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a018c3abb1c819083e802ac79ff4c34 completed May 11, 2026, 7:58 a.m.
Created at: April 10, 2026, 5:38 a.m.