Triple

T28662666
Position Surface form Disambiguated ID Type / Status
Subject Liberatores E725507 entity
Predicate hasMember P10 FINISHED
Object Publius Servilius Casca
Publius Servilius Casca was a Roman politician and one of the leading assassins of Julius Caesar, traditionally identified as the first to strike during the attack on the dictator in 44 BC.
E1832536 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: Publius Servilius Casca | Statement: [Liberatores, hasMember, Publius Servilius Casca]
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: Publius Servilius Casca
Triple: [Liberatores, hasMember, Publius Servilius Casca]
Generated description
Publius Servilius Casca was a Roman politician and one of the leading assassins of Julius Caesar, traditionally identified as the first to strike during the attack on the dictator in 44 BC.

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_69f01d84f5f0819087ab5e6143b14ed7 completed April 28, 2026, 2:37 a.m.
NER Named-entity recognition batch_69f655a0e37c81908905edac75b7fa6c completed May 2, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a24a241fdc88190ad65bd1183fb10ce completed June 6, 2026, 10:42 p.m.
NEDg Description generation batch_6a24a6f288e081909be31fa656bde288 completed June 6, 2026, 11:02 p.m.
NED2 Entity disambiguation (via description) batch_6a24a7223d208190946359b40e7090da completed June 6, 2026, 11:02 p.m.
Created at: April 28, 2026, 4:59 a.m.