Triple

T36059913

Position	Surface form	Disambiguated ID	Type / Status
Subject	Donnie Darko	`E1043046`	entity
Predicate	inUniverseAuthorInfluence	`P134940`	FINISHED
Object	Roberta Sparrow (Grandma Death) Roberta Sparrow, also known as Grandma Death, is a reclusive former nun and author of the pivotal book "The Philosophy of Time Travel" in the film Donnie Darko, whose writings underpin the movie’s exploration of time and destiny.	`E2166073`	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: Roberta Sparrow (Grandma Death) | Statement: [Donnie Darko, inUniverseAuthorInfluence, Roberta Sparrow (Grandma Death)]

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: Roberta Sparrow (Grandma Death)
Triple: [Donnie Darko, inUniverseAuthorInfluence, Roberta Sparrow (Grandma Death)]

Generated description

Roberta Sparrow, also known as Grandma Death, is a reclusive former nun and author of the pivotal book "The Philosophy of Time Travel" in the film Donnie Darko, whose writings underpin the movie’s exploration of time and destiny.

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

Target predicate: inUniverseAuthorInfluence
Context triple: [Donnie Darko, inUniverseAuthorInfluence, Roberta Sparrow (Grandma Death)]

A. influencesFromAuthor chosen
Indicates that one entity is affected or shaped by the actions, ideas, or characteristics of an author.
B. inUniverseAuthorHome
Indicates that a location is the canonical home or primary residence of an author within a fictional universe.
C. impactOnAuthor
Indicates that one entity has an effect, influence, or consequence on the author.
D. workAuthoredInUniverse
Indicates that a creative work is set within, or narratively belongs to, a particular fictional or conceptual universe.
E. hasInfluentialAuthor
Indicates that an entity has an author whose work has had significant impact or influence in a relevant domain.
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_69f76e2f09448190b0486d5ecad5e243`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_69fd2a215d6c8190a1a428ccaee603f1`	completed	May 8, 2026, 12:11 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a38cba75210819090607cf949aa519c`	completed	June 22, 2026, 5:44 a.m.
NEDg	Description generation	`batch_6a38cc3abea481908142bfac68c1f7ee`	completed	June 22, 2026, 5:46 a.m.
NED2	Entity disambiguation (via description)	`batch_6a38cd14a5f48190b924f3818ebdf8e7`	completed	June 22, 2026, 5:50 a.m.
PD	Predicate disambiguation	`batch_69fd28ef19688190bb8370f2812a43e7`	completed	May 8, 2026, 12:06 a.m.

Created at: May 3, 2026, 4:08 p.m.