Triple

T37012728

Position	Surface form	Disambiguated ID	Type / Status
Subject	Emily Kaldwin	`E915990`	entity
Predicate	regainsThroneIn	`P73419`	FINISHED
Object	Dishonored 2 Dishonored 2 is a first-person stealth-action video game by Arkane Studios and Bethesda Softworks, set in a richly detailed steampunk world where players can control either Empress Emily Kaldwin or her protector Corvo Attano to reclaim a usurped throne.	`E266332`	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: Dishonored 2 | Statement: [Emily Kaldwin, regainsThroneIn, Dishonored 2]

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: Dishonored 2
Triple: [Emily Kaldwin, regainsThroneIn, Dishonored 2]

Generated description

Dishonored 2 is a first-person stealth-action video game by Arkane Studios and Bethesda Softworks, set in a richly detailed steampunk world where players can control either Empress Emily Kaldwin or her protector Corvo Attano to reclaim a usurped throne.

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

Target predicate: regainsThroneIn
Context triple: [Emily Kaldwin, regainsThroneIn, Dishonored 2]

A. regainsThroneFrom
Indicates that one entity takes back control of a throne or rulership position that had been held by another entity.
B. restoredToThroneBy
Indicates that an entity was returned to a position of rulership or kingship through the actions or intervention of another entity.
C. restoredToThrone chosen
Indicates that an entity regains a previously held throne or royal position after having lost or been removed from it.
D. ascendedToThroneIn
Indicates the time or place at which a person formally became the ruling monarch or assumed the throne.
E. placedOnThrone
Indicates that an entity is formally elevated to a position of rulership or authority, typically by being seated on a throne.
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_69f76e90ed548190b187d2475f5c807d`	completed	May 3, 2026, 3:49 p.m.
NER	Named-entity recognition	`batch_69fb154c0fe08190a2e41e7a29b6055f`	completed	May 6, 2026, 10:17 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a46dad2bea08190a43d17a71ee0c7d8`	completed	July 2, 2026, 9:40 p.m.
NEDg	Description generation	`batch_6a46dbac01f48190bba3032c30daf73f`	completed	July 2, 2026, 9:44 p.m.
NED2	Entity disambiguation (via description)	`batch_6a46f3b413ac819080a7216c7f187060`	completed	July 2, 2026, 11:26 p.m.
PD	Predicate disambiguation	`batch_69f9fecc005c8190be082a8689193745`	completed	May 5, 2026, 2:29 p.m.

Created at: May 3, 2026, 4:14 p.m.