Triple

T34561402

Position	Surface form	Disambiguated ID	Type / Status
Subject	Jason King	`E887349`	entity
Predicate	hasFictionalWorkWithinShow	`P56229`	FINISHED
Object	Mark Caine novels The Mark Caine novels are a series of fictional spy-thriller books written by the flamboyant author-character Jason King within the British television series "Department S" and its spin-off "Jason King."	`E2101697`	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: Mark Caine novels | Statement: [Jason King, hasFictionalWorkWithinShow, Mark Caine novels]

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: Mark Caine novels
Triple: [Jason King, hasFictionalWorkWithinShow, Mark Caine novels]

Generated description

The Mark Caine novels are a series of fictional spy-thriller books written by the flamboyant author-character Jason King within the British television series "Department S" and its spin-off "Jason King."

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

Target predicate: hasFictionalWorkWithinShow
Context triple: [Jason King, hasFictionalWorkWithinShow, Mark Caine novels]

A. hasFictionalWork chosen
Indicates that one entity is the creator, owner, or source of a fictional work associated with another entity.
B. hasFictionalShowWithinShow
Indicates that one show contains or features another fictional show within its narrative.
C. hasFictionalRole
Indicates that an entity plays or is assigned a specific role within a fictional work or narrative.
D. worksWithFictionalCharacter
Indicates that one entity collaborates or interacts in a work-related context with another entity that is a fictional character.
E. hasFictionalFilmWithinPlay
Indicates that within a theatrical play, there is a fictional film that exists or is depicted as part of the play’s narrative or structure.
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_69f349d0c4d881908dd0950f5eb9ec0a`	completed	April 30, 2026, 12:23 p.m.
NER	Named-entity recognition	`batch_69ff76ac40988190a34d858b5472ee2b`	completed	May 9, 2026, 6:02 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a37362840a08190a5339cef226a93c0`	completed	June 21, 2026, 12:54 a.m.
NEDg	Description generation	`batch_6a3736d2432c819083dc2022f6d5b181`	completed	June 21, 2026, 12:56 a.m.
NED2	Entity disambiguation (via description)	`batch_6a37375fecf081908a85fdb46751fc6b`	completed	June 21, 2026, 12:59 a.m.
PD	Predicate disambiguation	`batch_69ff760a90948190a12fcb80e6e3e14b`	completed	May 9, 2026, 5:59 p.m.

Created at: May 1, 2026, 2:02 a.m.