Triple

T28035246
Position Surface form Disambiguated ID Type / Status
Subject Edzard Ernst E708386 entity
Predicate awardReceived P11 FINISHED
Object John Maddox Prize
The John Maddox Prize is an international award that honors individuals who promote sound science and evidence-based reasoning in the face of hostility or difficulty.
 E1800313 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: John Maddox Prize | Statement: [Edzard Ernst, awardReceived, John Maddox Prize]
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: John Maddox Prize
Triple: [Edzard Ernst, awardReceived, John Maddox Prize]
Generated description
The John Maddox Prize is an international award that honors individuals who promote sound science and evidence-based reasoning in the face of hostility or difficulty.

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_69ef9b6bdd9c8190bb3a574a03774ad1 completed April 27, 2026, 5:22 p.m.
NER Named-entity recognition batch_69f63c75d5748190a4b425f32054bff5 completed May 2, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15b8b29cdc819085ce9da089bda72f completed May 26, 2026, 3:13 p.m.
NEDg Description generation batch_6a15bb3677548190ac6801da25e5889d completed May 26, 2026, 3:24 p.m.
NED2 Entity disambiguation (via description) batch_6a15bbd99e648190a306d2b62654a4d7 completed May 26, 2026, 3:27 p.m.
Created at: April 27, 2026, 8:20 p.m.