Triple

T30707404
Position Surface form Disambiguated ID Type / Status
Subject Lullingstone Roman Villa E781788 entity
Predicate excavatedBy P7650 FINISHED
Object George W. Meates
George W. Meates was an archaeologist best known for leading the excavation and study of the Lullingstone Roman Villa in Kent, England.
E2029444 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: George W. Meates | Statement: [Lullingstone Roman Villa, excavatedBy, George W. Meates]
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: George W. Meates
Triple: [Lullingstone Roman Villa, excavatedBy, George W. Meates]
Generated description
George W. Meates was an archaeologist best known for leading the excavation and study of the Lullingstone Roman Villa in Kent, England.

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_69f224abfcf081909492e64d3cc35262 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f68c1b0d888190b443f6c77569bc77 completed May 2, 2026, 11:43 p.m.
NED1 Entity disambiguation (via context triple) batch_6a34d23b5e1081908d6e453c684075cd completed June 19, 2026, 5:23 a.m.
NEDg Description generation batch_6a34d32a229481909a407bea93892806 completed June 19, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_6a34d3ab5e98819091f34300bf83621d completed June 19, 2026, 5:29 a.m.
Created at: April 29, 2026, 8:35 p.m.