Triple

T24783485
Position Surface form Disambiguated ID Type / Status
Subject Unseen University E620059 entity
Predicate employs P7 FINISHED
Object the Librarian
The Librarian is the orangutan in charge of the magical library at Unseen University in Terry Pratchett’s Discworld series, known for his single-word vocabulary of “Oook” and fierce devotion to the books.
E1662959 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: the Librarian | Statement: [Unseen University, employs, the Librarian]
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: the Librarian
Triple: [Unseen University, employs, the Librarian]
Generated description
The Librarian is the orangutan in charge of the magical library at Unseen University in Terry Pratchett’s Discworld series, known for his single-word vocabulary of “Oook” and fierce devotion to the books.

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_6a104884cad88190a0f47c0a8fb1a2d6 completed May 22, 2026, 12:13 p.m.
NEDg Description generation batch_6a104a6d40f88190941fae4e53c175f7 completed May 22, 2026, 12:22 p.m.
NED2 Entity disambiguation (via description) batch_6a104c2d8308819097b21b979944585e completed May 22, 2026, 12:29 p.m.
Created at: April 18, 2026, 4:45 a.m.