Triple

T12536010
Position Surface form Disambiguated ID Type / Status
Subject Leiston E299690 entity
Predicate hasReligiousSite P916 FINISHED
Object Leiston Abbey E989086 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: Leiston Abbey | Statement: [Leiston, hasReligiousSite, Leiston Abbey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leiston Abbey
Context triple: [Leiston, hasReligiousSite, Leiston Abbey]
  • A. Leiston Abbey chosen
    Leiston Abbey is a historic ruined medieval monastery in Suffolk, England, known for its picturesque remains and significance in the region’s religious and architectural heritage.
  • B. Bisham Abbey
    Bisham Abbey is a historic manor house and former Augustinian monastery on the River Thames in Berkshire, England, now used as a national sports centre.
  • C. Beauchief Abbey
    Beauchief Abbey is a former medieval monastic house in Sheffield, England, now a historic ruin and church site set within parkland.
  • D. Carfax Abbey
    Carfax Abbey is a gloomy, abandoned estate in Bram Stoker’s novel "Dracula," serving as one of Count Dracula’s English strongholds.
  • E. Hailes Abbey
    Hailes Abbey is a former Cistercian monastery in Gloucestershire, England, renowned in the Middle Ages as a major pilgrimage site and now preserved as a historic ruin.
  • 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546d3b2081908d3e0659f8f13678 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65eb10618819092540de09997a0c5 completed May 2, 2026, 8:29 p.m.
Created at: April 8, 2026, 9:57 p.m.