Triple

T25788151
Position Surface form Disambiguated ID Type / Status
Subject William FitzOsbern E649476 entity
Predicate child P120 FINISHED
Object Roger de Breteuil, 2nd Earl of Hereford
Roger de Breteuil, 2nd Earl of Hereford, was an Anglo-Norman nobleman who played a leading role in the 1075 Revolt of the Earls against William the Conqueror.
E1694446 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: Roger de Breteuil, 2nd Earl of Hereford | Statement: [William FitzOsbern, child, Roger de Breteuil, 2nd Earl of Hereford]
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: Roger de Breteuil, 2nd Earl of Hereford
Triple: [William FitzOsbern, child, Roger de Breteuil, 2nd Earl of Hereford]
Generated description
Roger de Breteuil, 2nd Earl of Hereford, was an Anglo-Norman nobleman who played a leading role in the 1075 Revolt of the Earls against William the Conqueror.

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_69e7ab33e9308190afe415dc6f9e8876 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f5fefc58ac8190a770987f2b7b641b completed May 2, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10cc2a56e08190b89e5f3fe4fcd02a completed May 22, 2026, 9:35 p.m.
NEDg Description generation batch_6a10ccbbd8748190af5429ed417fd61f completed May 22, 2026, 9:38 p.m.
NED2 Entity disambiguation (via description) batch_6a10cdbc645881909f0c2da445ee41f6 completed May 22, 2026, 9:42 p.m.
Created at: April 22, 2026, 5:57 a.m.