Triple
T97214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cambridge University Library |
E1958
|
entity |
| Predicate | hasSpecialCollection |
P426
|
FINISHED |
| Object | medieval manuscripts |
—
|
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: medieval manuscripts | Statement: [Cambridge University Library, hasSpecialCollection, medieval manuscripts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialCollection Context triple: [Cambridge University Library, hasSpecialCollection, medieval manuscripts]
-
A.
hasSpecialUnit
Indicates that an entity possesses or is associated with a distinct, designated unit that has a special role, function, or status.
-
B.
hasCollection
chosen
Indicates that an entity possesses, maintains, or is associated with a set or group of related items treated as a collection.
-
C.
hasSpecialty
Indicates that an entity possesses a particular area of expertise, focus, or professional specialization.
-
D.
collects
Indicates that one entity gathers, accumulates, or brings together one or more other entities into its possession or control.
-
E.
collectibleAspect
Indicates that one entity represents a collectible-related characteristic, feature, or dimension associated with another entity.
- 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_69a24d4862f881908cc8b89d3a78031d |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a250cb400c8190b56343bbe19b48c7 |
completed | Feb. 28, 2026, 2:19 a.m. |
| PD | Predicate disambiguation | batch_69a24ebd19c48190bab291fea0ecc0c2 |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:09 a.m.