Triple

T17626137
Position Surface form Disambiguated ID Type / Status
Subject HMS Lion E429846 entity
Predicate homePort P3150 FINISHED
Object Rosyth 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: Rosyth | Statement: [HMS Lion, homePort, Rosyth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosyth
Context triple: [HMS Lion, homePort, Rosyth]
  • A. Rosyth chosen
    Rosyth is a Scottish port town on the north shore of the Firth of Forth, known for its naval dockyard and ferry connections.
  • B. Leuchars
    Leuchars is a village in Fife, Scotland, known for its nearby former RAF base and its railway station serving as a key access point for St Andrews.
  • C. Bonnington
    Bonnington is a district of Edinburgh, Scotland, situated along the Water of Leith and known for its mix of historic industrial buildings and residential areas.
  • D. Castlemartin
    Castlemartin is a small rural village in Pembrokeshire, Wales, known for its proximity to scenic coastal areas and a major military training range.
  • E. Limehurst
    Limehurst is a locality in Greater Manchester, England, situated near the village of Woodhouses.
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbc62e88190b9757dc7c52d7fee completed April 19, 2026, 5:53 a.m.
Created at: April 10, 2026, 5:52 a.m.