Triple

T30002200
Position Surface form Disambiguated ID Type / Status
Subject Michael Eavis E762199 entity
Predicate spouse P13 FINISHED
Object Elizabeth Eavis
Elizabeth Eavis was the wife of Michael Eavis, the English dairy farmer and founder of the Glastonbury Festival.
E1897915 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: Elizabeth Eavis | Statement: [Michael Eavis, spouse, Elizabeth Eavis]
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: Elizabeth Eavis
Triple: [Michael Eavis, spouse, Elizabeth Eavis]
Generated description
Elizabeth Eavis was the wife of Michael Eavis, the English dairy farmer and founder of the Glastonbury Festival.

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_69f2246a47ac81909cf5213053687ffc completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f6794fa4008190bd8861c7934bf8fe completed May 2, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a273226d6448190aeb2467715fe30a5 completed June 8, 2026, 9:20 p.m.
NEDg Description generation batch_6a273412bb148190b807e5f7054478e3 completed June 8, 2026, 9:28 p.m.
NED2 Entity disambiguation (via description) batch_6a2734afdee081908b9e8400be7766da completed June 8, 2026, 9:31 p.m.
Created at: April 29, 2026, 6:41 p.m.