Triple

T29006740
Position Surface form Disambiguated ID Type / Status
Subject Lord Lloyd of Berwick E736456 entity
Predicate nobleTitle P914 FINISHED
Object Baron Lloyd of Berwick
Baron Lloyd of Berwick is a British life peer and former senior judge who served as a Lord of Appeal in Ordinary in the House of Lords.
E1855305 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: Baron Lloyd of Berwick | Statement: [Lord Lloyd of Berwick, nobleTitle, Baron Lloyd of Berwick]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Baron Lloyd of Berwick
Triple: [Lord Lloyd of Berwick, nobleTitle, Baron Lloyd of Berwick]
Generated description
Baron Lloyd of Berwick is a British life peer and former senior judge who served as a Lord of Appeal in Ordinary in the House of Lords.

Provenance (5 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_69f077eb81e88190ad9ff62cbb9f555e completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_69f65fc08c78819086abfcb2c02af163 completed May 2, 2026, 8:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a25699db0008190825341f30e4b3d3f completed June 7, 2026, 12:52 p.m.
NEDg Description generation batch_6a256da280f081909ef24f37f6eaf0af completed June 7, 2026, 1:09 p.m.
NED2 Entity disambiguation (via description) batch_6a257152da848190a8a013cd159d7032 completed June 7, 2026, 1:25 p.m.
Created at: April 28, 2026, 9:38 a.m.