Triple
T30247738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caesar of the West |
E769102
|
entity |
| Predicate | hasImperialCollegeSize |
P179048
|
FINISHED |
| Object | four rulers |
—
|
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: four rulers | Statement: [Caesar of the West, hasImperialCollegeSize, four rulers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasImperialCollegeSize Context triple: [Caesar of the West, hasImperialCollegeSize, four rulers]
-
A.
imperialCollege
Indicates that one entity is Imperial College (typically as an affiliation, location, or institutional relationship) in relation to another entity.
-
B.
imperialCollegeRelation
Indicates a relationship where one entity is connected to Imperial College (e.g., by affiliation, attendance, employment, or collaboration) in some defined way.
-
C.
campusSize
Indicates the physical extent or scale of a campus, typically measured in area or capacity.
-
D.
hasFacultySizeApprox
Indicates that an institution has an approximate number of faculty members equal to the specified value.
-
E.
isLargestCampusOf
Indicates that one campus is the largest (by size, area, or capacity) among all campuses belonging to a particular institution or organization.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f719cc31ec819099bebcf833b14d76 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69f71995853c8190912025c0e83640c8 |
completed | May 3, 2026, 9:47 a.m. |
Created at: April 29, 2026, 7:39 p.m.