Triple

T7913350
Position Surface form Disambiguated ID Type / Status
Subject High Street E183753 entity
Predicate hasTopoMap P10300 FINISHED
Object OS Landranger 90 E617943 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: OS Landranger 90 | Statement: [High Street, hasTopoMap, OS Landranger 90]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OS Landranger 90
Context triple: [High Street, hasTopoMap, OS Landranger 90]
  • A. OS Landranger 90 chosen
    OS Landranger 90 is a detailed Ordnance Survey topographic map covering part of the English Lake District, including areas such as Loughrigg Fell.
  • B. OS Landranger 97
    OS Landranger 97 is a 1:50,000 scale Ordnance Survey map covering the area around Clougha Pike and its surrounding region.
  • C. OS Landranger 89
    OS Landranger 89 is a 1:50,000 scale Ordnance Survey map covering the area of Scafell Pike and its surrounding Lake District terrain, used for outdoor navigation and hiking.
  • D. OS Landranger 69
    OS Landranger 69 is a 1:50,000 scale Ordnance Survey topographic map covering the Isle of Arran and surrounding areas of southwest Scotland.
  • E. OS Landranger 110
    OS Landranger 110 is a 1:50,000 scale Ordnance Survey topographic map covering the area around Black Hill and its surrounding region in the UK.
  • 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_69ca828dec0c81908b8f55a4dbbb53ff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a748f4c8190bcd868de2fcf0b3a completed March 31, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5bdfb8d0819089cf1268df61bcdc completed March 31, 2026, 5:30 a.m.
Created at: March 30, 2026, 5:04 p.m.