Triple

T24783124
Position Surface form Disambiguated ID Type / Status
Subject Witches novels E620053 entity
Predicate setting P1957 FINISHED
Object kingdom of Lancre
The kingdom of Lancre is a small, mountainous, and magically-inclined fictional country in Terry Pratchett’s Discworld series, best known as the home of Granny Weatherwax and the other witches.
E1651670 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 Lancre | Statement: [Witches novels, setting, kingdom of Lancre]
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 Lancre
Triple: [Witches novels, setting, kingdom of Lancre]
Generated description
The kingdom of Lancre is a small, mountainous, and magically-inclined fictional country in Terry Pratchett’s Discworld series, best known as the home of Granny Weatherwax and the other witches.

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_69e2fabdbe8c8190adbb9434b8636cad completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f410d7fe908190b669acafdbee766a completed May 1, 2026, 2:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a101c2357fc8190bb048035797afc9f completed May 22, 2026, 9:04 a.m.
NEDg Description generation batch_6a1025b941fc819081957c8e7d21b7f1 completed May 22, 2026, 9:45 a.m.
NED2 Entity disambiguation (via description) batch_6a10265a02e08190b628804a79f31882 completed May 22, 2026, 9:48 a.m.
Created at: April 18, 2026, 4:45 a.m.