Triple

T29948985
Position Surface form Disambiguated ID Type / Status
Subject Demon's Souls (2009) E760718 entity
Predicate setting P1957 FINISHED
Object kingdom of Boletaria
The kingdom of Boletaria is a dark, fog-shrouded fantasy realm overrun by demons and soul-devouring horrors in the action role-playing game Demon's Souls.
E1892103 NE FINISHED

How this triple was built (2 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: kingdom of Boletaria | Statement: [Demon's Souls (2009), setting, kingdom of Boletaria]
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: kingdom of Boletaria
Triple: [Demon's Souls (2009), setting, kingdom of Boletaria]
Generated description
The kingdom of Boletaria is a dark, fog-shrouded fantasy realm overrun by demons and soul-devouring horrors in the action role-playing game Demon's Souls.

Provenance (5 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_69f2246562b881909d57622f4086d43d completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f6780dd5d08190b1ef4e49405a5419 completed May 2, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_6a271430dd58819087056990ec106dfb completed June 8, 2026, 7:12 p.m.
NEDg Description generation batch_6a27151f69408190952d4d3ad9a3fc38 completed June 8, 2026, 7:16 p.m.
NED2 Entity disambiguation (via description) batch_6a2718ad777081909ac0744b1551af12 completed June 8, 2026, 7:31 p.m.
Created at: April 29, 2026, 6:25 p.m.