Triple

T34588689

Position	Surface form	Disambiguated ID	Type / Status
Subject	Sparks (mad scientists)	`E888116`	entity
Predicate	hasInUniverseTerm	`P2920`	FINISHED
Object	Spark Spark is the in-universe term for the quasi-mystical, often hereditary genius that drives the reality-warping mad scientists in the Girl Genius webcomic.	`E2101857`	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: Spark | Statement: [Sparks (mad scientists), hasInUniverseTerm, Spark]

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: Spark
Triple: [Sparks (mad scientists), hasInUniverseTerm, Spark]

Generated description

Spark is the in-universe term for the quasi-mystical, often hereditary genius that drives the reality-warping mad scientists in the Girl Genius webcomic.

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

Target predicate: hasInUniverseTerm
Context triple: [Sparks (mad scientists), hasInUniverseTerm, Spark]

A. hasNameInUniverse
Indicates that an entity is known by a particular name within a specific fictional or defined universe.
B. hasTerm chosen
Indicates that an entity includes, is associated with, or is defined by a specific term or condition.
C. hasInUniverseLocationRelation
Indicates a relationship where an entity is associated with, or situated at, a specific location within a fictional or defined universe or setting.
D. inUniverseType
Indicates that one entity exists within, or is categorized as belonging to, a particular fictional or conceptual universe type defined by the other entity.
E. hasLanguageInUniverse
Indicates that a particular language exists or is used within a specified fictional or conceptual universe.
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_69f349d3bfcc81909874c99e646fb3ea`	completed	April 30, 2026, 12:23 p.m.
NER	Named-entity recognition	`batch_6a00372ff0e48190b3ed91f9bae9da6c`	completed	May 10, 2026, 7:43 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3748e0fa50819098edf44aae80c5ff`	completed	June 21, 2026, 2:13 a.m.
NEDg	Description generation	`batch_6a3749e579008190b045e083d4b1c7d9`	completed	June 21, 2026, 2:18 a.m.
NED2	Entity disambiguation (via description)	`batch_6a374a7a28d881908ea4fc55b7f0441b`	completed	June 21, 2026, 2:20 a.m.
PD	Predicate disambiguation	`batch_6a00359c1b8481909c1e43df9f5a789a`	completed	May 10, 2026, 7:37 a.m.

Created at: May 1, 2026, 2:03 a.m.