Triple

T20633813
Position Surface form Disambiguated ID Type / Status
Subject OS Landranger 47 E507023 entity
Predicate mapSeries P30997 FINISHED
Object OS Landranger 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: OS Landranger | Statement: [OS Landranger 47, mapSeries, OS Landranger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OS Landranger
Context triple: [OS Landranger 47, mapSeries, OS Landranger]
  • A. OS Landranger chosen
    OS Landranger is a series of 1:50,000 scale topographic maps produced by Ordnance Survey covering Great Britain for outdoor and recreational use.
  • B. OS Landranger 32
    OS Landranger 32 is a 1:50,000 scale Ordnance Survey map covering the Skye and Lochalsh area of northwest Scotland, including the Cuillin mountains.
  • C. OS Landranger 50
    OS Landranger 50 is a 1:50,000 scale Ordnance Survey topographic map covering the area around Loch Lomond and the southern Highlands of Scotland.
  • D. OS Landranger 80
    OS Landranger 80 is a 1:50,000 scale Ordnance Survey topographic map covering part of Northumberland and the Cheviot Hills area in northern England.
  • E. OS Landranger 72
    OS Landranger 72 is a 1:50,000 scale Ordnance Survey topographic map covering part of southern Scotland, including the area around Broad Law.
  • 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_69e0b4bd4a0081908d4e97a590a33fb2 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6ad0d808c81908a60abd02a22ed92 completed April 20, 2026, 10:47 p.m.
Created at: April 16, 2026, 11:42 a.m.