Triple

T26592545
Position Surface form Disambiguated ID Type / Status
Subject Hell Ride E667398 entity
Predicate castMember P1668 FINISHED
Object Francesca DeRosa
Francesca DeRosa is an actress known for her role in the outlaw biker film "Hell Ride."
E1789400 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: Francesca DeRosa | Statement: [Hell Ride, castMember, Francesca DeRosa]
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: Francesca DeRosa
Triple: [Hell Ride, castMember, Francesca DeRosa]
Generated description
Francesca DeRosa is an actress known for her role in the outlaw biker film "Hell Ride."

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_69ee9cfc385081909ac9ae178030a06e completed April 26, 2026, 11:17 p.m.
NER Named-entity recognition batch_69f61526a8ac8190bd40968b613985be completed May 2, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12ec8844f081909f767e6a06aef37b completed May 24, 2026, 12:18 p.m.
NEDg Description generation batch_6a12ed678580819082d28135e3fcb818 completed May 24, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_6a12eef15e2c819099088626fb78adce completed May 24, 2026, 12:28 p.m.
Created at: April 27, 2026, 2:08 a.m.