Triple

T6857383
Position Surface form Disambiguated ID Type / Status
Subject Rosewell E158181 entity
Predicate locatedNear P294 FINISHED
Object Dalkeith E280754 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: Dalkeith | Statement: [Rosewell, locatedNear, Dalkeith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dalkeith
Context triple: [Rosewell, locatedNear, Dalkeith]
  • A. Dalkeith chosen
    Dalkeith is a historic town in Midlothian, Scotland, known for its market-town heritage and proximity to Edinburgh.
  • B. Penicuik
    Penicuik is a small Scottish town situated to the south of Edinburgh, known historically for its paper mills and proximity to the Pentland Hills.
  • C. Cardenden
    Cardenden is a village in Fife, Scotland, known primarily as a former mining community with a railway station on the local commuter network.
  • D. Dalmellington
    Dalmellington is a small village in East Ayrshire, Scotland, known as a gateway to the nearby Galloway Hills and surrounding upland countryside.
  • E. Kirkliston
    Kirkliston is a small town and former village in Scotland, situated to the west of Edinburgh and known for its historic parish church and role as a commuter settlement for the capital.
  • 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_69c68830cdbc8190a8301c7a9d9f651a completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d870a8088190b42fde7626735cb1 completed March 27, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69ccbd5d671481908ecbdb8ce6ef898a completed April 1, 2026, 6:38 a.m.
Created at: March 27, 2026, 2:21 p.m.