Triple

T37595472

Position	Surface form	Disambiguated ID	Type / Status
Subject	Quentin Tarantino universe	`E935372`	entity
Predicate	includesFictionalBrand	`P114832`	FINISHED
Object	Red Apple Cigarettes Red Apple Cigarettes is a recurring fictional cigarette brand that appears throughout Quentin Tarantino’s films as a signature in-universe product and visual motif.	`E1205333`	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: Red Apple Cigarettes | Statement: [Quentin Tarantino universe, includesFictionalBrand, Red Apple Cigarettes]

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: Red Apple Cigarettes
Triple: [Quentin Tarantino universe, includesFictionalBrand, Red Apple Cigarettes]

Generated description

Red Apple Cigarettes is a recurring fictional cigarette brand that appears throughout Quentin Tarantino’s films as a signature in-universe product and visual motif.

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

Target predicate: includesFictionalBrand
Context triple: [Quentin Tarantino universe, includesFictionalBrand, Red Apple Cigarettes]

A. hasFictionalProduct chosen
Indicates a relationship where one entity features, offers, or includes a product that exists only in fiction or an imagined context.
B. fictionalBrand
Indicates that one entity is a brand that exists only in fiction or narrative contexts, rather than in the real world.
C. hasFictionalMarketing
Indicates that an entity is associated with marketing materials or campaigns that are fictional, fabricated, or not based on real products, services, or events.
D. containsFictionalOrganization
Indicates that one entity includes or features a fictional organization as part of its content or composition.
E. hasFictionalPackaging
Indicates that an item is presented or wrapped in packaging that is imaginary, simulated, or not used in real-world distribution.
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_69f76ecf39c081909baffe597bb55273`	completed	May 3, 2026, 3:50 p.m.
NER	Named-entity recognition	`batch_6a037c8efcd4819088c2aeead65d93df`	completed	May 12, 2026, 7:16 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a40a802c9cc8190a82c53bc8095a477`	completed	June 28, 2026, 4:50 a.m.
NEDg	Description generation	`batch_6a40a93f15e481909584730b9d6a8ca1`	completed	June 28, 2026, 4:55 a.m.
NED2	Entity disambiguation (via description)	`batch_6a40a9c509e48190803e29dc13c1ce8d`	completed	June 28, 2026, 4:57 a.m.
PD	Predicate disambiguation	`batch_6a037a1553e08190bb7424c448cb1f33`	completed	May 12, 2026, 7:05 p.m.

Created at: May 3, 2026, 4:18 p.m.