Triple
T25705388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harleian Library |
E644574
|
entity |
| Predicate | employedLibrarian |
P138208
|
FINISHED |
| Object | Humphrey Wanley |
—
|
NE NERFINISHED |
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: Humphrey Wanley | Statement: [Harleian Library, employedLibrarian, Humphrey Wanley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employedLibrarian Context triple: [Harleian Library, employedLibrarian, Humphrey Wanley]
-
A.
hasLibrarian
chosen
Indicates that an entity is associated with or served by a specific librarian.
-
B.
employedTo
Indicates that one entity is hired or engaged to perform work, services, or duties for another entity.
-
C.
employedRole
Indicates that an entity holds or performs a specific role or position within an employment or work context.
-
D.
employedThrough
Indicates that an entity holds a job or work position by means of, or via the arrangement of, another entity (such as an agency, contractor, or intermediary).
-
E.
library
Indicates that an entity functions as or is associated with a library, typically as a place or system for storing, organizing, and providing access to collections of information resources.
- F. None of above.
Provenance (3 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_69e77e83c8ec8190bf52fcdac4838984 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6456608190b94e7c2e2c2a4824 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 21, 2026, 9:03 p.m.