Triple
T8963007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kisumu Campus |
E214053
|
entity |
| Predicate | hasNetworkMembership |
P27891
|
FINISHED |
| Object | University of Nairobi campuses network |
—
|
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: University of Nairobi campuses network | Statement: [Kisumu Campus, hasNetworkMembership, University of Nairobi campuses network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNetworkMembership Context triple: [Kisumu Campus, hasNetworkMembership, University of Nairobi campuses network]
-
A.
hasMembershipBy
Indicates that an entity holds or acquires membership in a group, organization, or program by means of a specified agent, process, or instrument.
-
B.
hasRoleInNetwork
Indicates that an entity holds a specific functional position or responsibility within a particular network.
-
C.
hasMembershipBase
Indicates that an entity possesses or is associated with a foundational group or set of members that form its membership base.
-
D.
hasMembers
Indicates that a group, organization, or collection includes certain entities as its members.
-
E.
membershipIn
chosen
Indicates that an entity belongs to, is part of, or holds membership in a particular group, organization, or collection.
- 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_69ca839cd6008190a1546a701a56710c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6749e5008190a01f42a2e772dd54 |
completed | April 1, 2026, 12:31 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed74d288190b712d739805579dc |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:01 p.m.