Triple
T1224458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magdalene College, Cambridge |
E26294
|
entity |
| Predicate | isOldMemberOf |
P1168
|
FINISHED |
| Object | Cambridge colleges on the River Cam |
—
|
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: Cambridge colleges on the River Cam | Statement: [Magdalene College, Cambridge, isOldMemberOf, Cambridge colleges on the River Cam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOldMemberOf Context triple: [Magdalene College, Cambridge, isOldMemberOf, Cambridge colleges on the River Cam]
-
A.
formerMemberOf
chosen
Indicates that an entity once belonged to or was affiliated with a group, organization, or body, but is no longer a member.
-
B.
membershipAsOf
Indicates that one entity is a member of another entity or group at a specific point in time or as of a given date.
-
C.
hasMemberFrom
Indicates that a group, organization, or collection includes at least one member originating from or belonging to a specified source, place, or category.
-
D.
hasAncientMember
Indicates that at least one member of a group, set, or collection originates from or belongs to an ancient time period.
-
E.
hasAssociateMember
Indicates that an entity has another entity connected to it in a non-full, typically limited or secondary, membership capacity.
- 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_69a49484688c8190a1bf285eb396a8b6 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4be382c4081909238c18b805352a7 |
completed | March 1, 2026, 10:31 p.m. |
| PD | Predicate disambiguation | batch_69a4bb644af08190ba25905f20adb01a |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.