Triple

T35115283

Position	Surface form	Disambiguated ID	Type / Status
Subject	Cannibal Ferox	`E1013415`	entity
Predicate	starring	`P1507`	FINISHED
Object	Lorraine De Selle Lorraine De Selle is an Italian actress best known for her roles in 1980s exploitation and horror films, particularly in the cannibal and women-in-prison subgenres.	`E2288376`	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: Lorraine De Selle | Statement: [Cannibal Ferox, starring, Lorraine De Selle]

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: Lorraine De Selle
Triple: [Cannibal Ferox, starring, Lorraine De Selle]

Generated description

Lorraine De Selle is an Italian actress best known for her roles in 1980s exploitation and horror films, particularly in the cannibal and women-in-prison subgenres.

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_69f76dd659d08190bcdc00d37caafb62`	completed	May 3, 2026, 3:46 p.m.
NER	Named-entity recognition	`batch_69f78c3758448190b350cb810dec52cb`	completed	May 3, 2026, 5:56 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a5a864b63b88190bead500f4a4221dc`	completed	July 17, 2026, 7:45 p.m.
NEDg	Description generation	`batch_6a5a8769d23c8190b535d9a132289c33`	completed	July 17, 2026, 7:50 p.m.
NED2	Entity disambiguation (via description)	`batch_6a5a890cc31c8190b00f18f5ee497f55`	completed	July 17, 2026, 7:57 p.m.

Created at: May 3, 2026, 4:01 p.m.