Triple

T4930901
Position Surface form Disambiguated ID Type / Status
Subject Strand, London E110691 entity
Predicate partOf P40 FINISHED
Object A4 road E69163 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: A4 road | Statement: [Strand, London, partOf, A4 road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A4 road
Context triple: [Strand, London, partOf, A4 road]
  • A. A4 road chosen
    The A4 road is a major historic route in England that runs west from central London through key cities such as Reading, Bath, and Bristol toward Avonmouth.
  • B. A5 road
    The A5 road is a major historic route in Great Britain running from London to Holyhead, forming part of the key connection between England and Wales.
  • C. A2 road
    The A2 road is a major route in southeast England connecting London to the port of Dover and forming part of a key corridor to mainland Europe.
  • D. A2 road
    The A2 road is a major coastal route in Northern Ireland that connects several key towns and cities along the north and east coasts.
  • E. A8 road
    The A8 road is a major route in the United Kingdom that connects Glasgow to Greenock in western Scotland, serving as an important link for regional and local traffic.
  • 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_69bd4415190c8190817bee7ec9f9f944 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd706245e48190a61d573438461c30 completed March 20, 2026, 4:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef26fd12c819082f644bc727584ec completed April 2, 2026, 10:49 p.m.
Created at: March 20, 2026, 1:30 p.m.