Triple

T15050977
Position Surface form Disambiguated ID Type / Status
Subject Shandon Bells and Tower E379358 entity
Predicate overlooks P1323 FINISHED
Object River Lee E178112 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: River Lee | Statement: [Shandon Bells and Tower, overlooks, River Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: River Lee
Context triple: [Shandon Bells and Tower, overlooks, River Lee]
  • A. River Lee chosen
    The River Lee is a major river in County Cork, Ireland, flowing through the city of Cork before emptying into Cork Harbour.
  • B. River Lee
    River Lee is a significant river in southeast England that flows through Hertfordshire and Essex before joining the River Thames in London.
  • C. River Douglas
    The River Douglas is a river in North West England that flows through Lancashire and Greater Manchester before joining the River Ribble estuary.
  • D. River Douglas
    River Douglas is a small river on the Isle of Man that flows through the island’s capital, Douglas, before reaching the Irish Sea.
  • E. River Okement
    The River Okement is a small river in Devon, England, that flows through the town of Okehampton before joining the River Torridge.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69deda8f71988190b4fe7f7de4ccb798 completed April 15, 2026, 12:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69fec878c52c8190bf010b1fd4d21f65 completed May 9, 2026, 5:39 a.m.
Created at: April 10, 2026, 3:01 a.m.