Triple

T33024457

Position	Surface form	Disambiguated ID	Type / Status
Subject	The Spider’s Feast	`E845000`	entity
Predicate	scenarist	`P34396`	FINISHED
Object	Gilbert de Voisins Gilbert de Voisins was a French writer and screenwriter active in the early 20th century, known for his contributions to literature and cinema.	`E2031934`	NE FINISHED

How this triple was built (3 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: Gilbert de Voisins | Statement: [The Spider’s Feast, scenarist, Gilbert de Voisins]

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: Gilbert de Voisins
Triple: [The Spider’s Feast, scenarist, Gilbert de Voisins]

Generated description

Gilbert de Voisins was a French writer and screenwriter active in the early 20th century, known for his contributions to literature and cinema.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: scenarist
Context triple: [The Spider’s Feast, scenarist, Gilbert de Voisins]

A. screenwriterInstanceOf
Indicates that a screenwriter belongs to or is classified as a specific type, category, or class of entity.
B. screenwriterCreator chosen
Indicates that one entity is the screenwriter who created or authored the screenplay for another entity (such as a film, episode, or audiovisual work).
C. screenwriterDepictionBy
Indicates a relationship where a screenwriter is portrayed or represented by another entity, such as in a work, record, or description.
D. screenwriterOfDepiction
Indicates that one entity is the screenwriter responsible for the script of a particular depiction or representation of a work or subject.
E. coScreenwriter
Indicates that two or more individuals collaborated in writing the screenplay for the same work.
F. None of above.

Provenance (6 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_69f34950749c8190ae05cd27adb16d58`	completed	April 30, 2026, 12:21 p.m.
NER	Named-entity recognition	`batch_69f6d74b20a48190900dda1014cc13a8`	completed	May 3, 2026, 5:04 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a34dadef0c881909415cd864af2a9af`	completed	June 19, 2026, 5:59 a.m.
NEDg	Description generation	`batch_6a34dbb1e474819095ca57b4364327cd`	completed	June 19, 2026, 6:03 a.m.
NED2	Entity disambiguation (via description)	`batch_6a34dc3d2df08190932ef2da9ac631ae`	completed	June 19, 2026, 6:05 a.m.
PD	Predicate disambiguation	`batch_69f6d26f27dc8190ae426a3e1573933e`	completed	May 3, 2026, 4:43 a.m.

Created at: May 1, 2026, 1:23 a.m.