Triple

T21800010
Position Surface form Disambiguated ID Type / Status
Subject Lawnmarket E538212 entity
Predicate connectsTo P845 FINISHED
Object Castlehill E305252 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: Castlehill | Statement: [Lawnmarket, connectsTo, Castlehill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Castlehill
Context triple: [Lawnmarket, connectsTo, Castlehill]
  • A. Castlehill chosen
    Castlehill is a historic street and area forming part of Edinburgh’s Old Town, located near Edinburgh Castle along the Royal Mile.
  • B. Sighthill
    Sighthill is a district in Edinburgh, Scotland, known for its residential areas, educational institutions, and urban regeneration projects.
  • C. Sighthill
    Sighthill is a residential district in the north of Glasgow, Scotland, known for its large-scale regeneration and proximity to the Springburn area.
  • D. Hillhead
    Hillhead is a vibrant district in Glasgow’s West End known for its proximity to the University of Glasgow, bustling Byres Road, and a mix of shops, cafes, and cultural venues.
  • E. Hillhead
    Hillhead is a central street in Lerwick, Shetland, known for hosting key civic buildings including Lerwick Town Hall.
  • 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_69e0c4733f4081909a86622e7e6d15d2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f077fede848190b8fe07941d6573d9 completed April 28, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e802e6c8190b14f0b8765dba15b completed May 17, 2026, 10:17 p.m.
Created at: April 16, 2026, 6:53 p.m.