Triple

T33344531

Position	Surface form	Disambiguated ID	Type / Status
Subject	Republic of Zubrowka	`E853758`	entity
Predicate	hasFictionalLegalSystem	`P122658`	FINISHED
Object	Zubrowkan courts Zubrowkan courts are the fictional judicial institutions of the Republic of Zubrowka, forming part of the imagined legal system in Wes Anderson’s narrative universe.	`E2047817`	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: Zubrowkan courts | Statement: [Republic of Zubrowka, hasFictionalLegalSystem, Zubrowkan courts]

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: Zubrowkan courts
Triple: [Republic of Zubrowka, hasFictionalLegalSystem, Zubrowkan courts]

Generated description

Zubrowkan courts are the fictional judicial institutions of the Republic of Zubrowka, forming part of the imagined legal system in Wes Anderson’s narrative universe.

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

Target predicate: hasFictionalLegalSystem
Context triple: [Republic of Zubrowka, hasFictionalLegalSystem, Zubrowkan courts]

A. hasFictionalJurisdictionOver
Indicates that one entity holds an imagined or narrative-based authority, control, or legal power over another within a fictional or hypothetical context.
B. fictionalJurisdiction chosen
Indicates that one entity has legal authority or governance over another within an invented or imaginary legal system or territory.
C. hasFictionalReligiousJurisdiction
Indicates that one entity holds an invented or fictional religious authority, control, or governance over another entity within a narrative or imaginary context.
D. hasFictionalWorldType
Indicates that an entity is associated with, set in, or characterized by a particular type or category of fictional world.
E. hasFictionalHierarchy
Indicates that one entity occupies a specific level, rank, or position within a fictional or imagined hierarchical structure defined by another entity.
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_69f3496a1a588190bad9cbe9221144e0`	completed	April 30, 2026, 12:22 p.m.
NER	Named-entity recognition	`batch_69ff21cbd9108190a52c0ba42004c669`	completed	May 9, 2026, noon
NED1	Entity disambiguation (via context triple)	`batch_6a3552073bfc8190871d116e62e2823f`	completed	June 19, 2026, 2:28 p.m.
NEDg	Description generation	`batch_6a355873f94c8190bc0b8380060a0a7e`	completed	June 19, 2026, 2:55 p.m.
NED2	Entity disambiguation (via description)	`batch_6a3558ddb0e48190becf4dc701bdee63`	completed	June 19, 2026, 2:57 p.m.
PD	Predicate disambiguation	`batch_69ff1faea91881908c626c70bca5100a`	completed	May 9, 2026, 11:51 a.m.

Created at: May 1, 2026, 1:34 a.m.