Triple

T28105773

Position	Surface form	Disambiguated ID	Type / Status
Subject	Shot Turquoise Marilyn	`E710357`	entity
Predicate	basedOnPhotographer	`P85016`	FINISHED
Object	Gene Korman Gene Korman was a photographer whose publicity image of Marilyn Monroe became the source material for Andy Warhol’s famous "Shot Turquoise Marilyn" silkscreen painting.	`E1801582`	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: Gene Korman | Statement: [Shot Turquoise Marilyn, basedOnPhotographer, Gene Korman]

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: Gene Korman
Triple: [Shot Turquoise Marilyn, basedOnPhotographer, Gene Korman]

Generated description

Gene Korman was a photographer whose publicity image of Marilyn Monroe became the source material for Andy Warhol’s famous "Shot Turquoise Marilyn" silkscreen painting.

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

Target predicate: basedOnPhotographer
Context triple: [Shot Turquoise Marilyn, basedOnPhotographer, Gene Korman]

A. basedOnBy
Indicates that one entity is derived from, justified by, or constructed using another entity as its source, foundation, or reference.
B. usesPhotographyFrom chosen
Indicates that one entity employs or incorporates photographic material originating from another entity.
C. photographer
Indicates that one entity takes photographs of another entity, typically in a professional or intentional capacity.
D. hasPhotographerNationality
Indicates that a photographer is associated with a specific nationality.
E. basedOnDesignBy
Indicates that something is created, developed, or structured according to the design conceived or produced by a specified 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_69ef9b71fdb081908b4a61cd7ff147c1`	completed	April 27, 2026, 5:22 p.m.
NER	Named-entity recognition	`batch_69f7be53890081909b1d93f30a8f31c6`	completed	May 3, 2026, 9:29 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a15c92aeac8819082627315b96bccd6`	completed	May 26, 2026, 4:24 p.m.
NEDg	Description generation	`batch_6a15c9d233048190a27d170dbe16c07e`	completed	May 26, 2026, 4:26 p.m.
NED2	Entity disambiguation (via description)	`batch_6a15ca83e4588190baed86972447f0f8`	completed	May 26, 2026, 4:29 p.m.
PD	Predicate disambiguation	`batch_69f7bccacbac8190978976324c67db28`	completed	May 3, 2026, 9:23 p.m.

Created at: April 27, 2026, 9:08 p.m.