Triple

T36679192
Position Surface form Disambiguated ID Type / Status
Subject British constitutional conventions E905628 entity
Predicate example P1259 FINISHED
Object Salisbury convention
The Salisbury convention is a key UK constitutional principle under which the House of Lords does not block legislation implementing commitments from the governing party’s election manifesto.
E2193949 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: Salisbury convention | Statement: [British constitutional conventions, example, Salisbury convention]
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: Salisbury convention
Triple: [British constitutional conventions, example, Salisbury convention]
Generated description
The Salisbury convention is a key UK constitutional principle under which the House of Lords does not block legislation implementing commitments from the governing party’s election manifesto.

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_69f76e7011dc819082b324f18b756a1b completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7c7a487408190b3a5ee144e651046 completed May 3, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3a20e007b48190a1f55d71d7d617ce completed June 23, 2026, 6 a.m.
NEDg Description generation batch_6a3a21a5d1f4819089fe5c6b52412012 completed June 23, 2026, 6:03 a.m.
NED2 Entity disambiguation (via description) batch_6a3a2219688881908f62dd0a5e70eced completed June 23, 2026, 6:05 a.m.
Created at: May 3, 2026, 4:12 p.m.