Triple
T20211308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blood quill |
E493491
|
entity |
| Predicate | usedInRoom |
P139229
|
FINISHED |
| Object | Dolores Umbridge's office |
—
|
LITERAL 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: Dolores Umbridge's office | Statement: [Blood quill, usedInRoom, Dolores Umbridge's office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInRoom Context triple: [Blood quill, usedInRoom, Dolores Umbridge's office]
-
A.
areUsedIn
Indicates that certain entities serve as components, tools, or resources within a particular process, context, or application.
-
B.
hasRoom
Indicates that an entity possesses, contains, or is associated with a specific room.
-
C.
usedInStructure
Indicates that something (such as a material, component, or element) is employed as part of the composition or construction of a larger structure.
-
D.
usedInPartOf
Indicates that something is utilized or plays a functional role within a specific component or subpart of a larger whole.
-
E.
alsoUsedIn
Indicates that something is additionally employed, applied, or present in another context, setting, or use case beyond the primary one.
- F. None of above. chosen
Provenance (4 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ed5691c8190bf253b1d4ee6e88f |
completed | April 20, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69e55b14c9d8819095453d0504d9222f |
completed | April 19, 2026, 10:45 p.m. |
| PDg | Predicate description generation | batch_69e56700b1a08190ace53cf95827d72d |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 11, 2026, 11:38 p.m.