Triple
T27070903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harley family |
E685321
|
entity |
| Predicate | collectionCoreOf |
P64483
|
FINISHED |
| Object | British Library manuscript collections |
—
|
NE NERFINISHED |
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: British Library manuscript collections | Statement: [Harley family, collectionCoreOf, British Library manuscript collections]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectionCoreOf Context triple: [Harley family, collectionCoreOf, British Library manuscript collections]
-
A.
collectionBy
Indicates that one entity is the collector or curator responsible for assembling, managing, or owning a particular collection of items represented by another entity.
-
B.
collectionRepository
Indicates a relationship where a repository is responsible for storing, managing, or providing access to a collection.
-
C.
collectionBuiltAround
chosen
Indicates that a collection is organized, structured, or conceptually centered around a particular core item, theme, or entity.
-
D.
collectionScope
Indicates the extent, boundaries, or range over which a collection (such as a set of items, data, or resources) is defined or intended to apply.
-
E.
collectionModel
Indicates that one entity serves as a model, template, or representative example for a collection of related entities.
- 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_69ef14843b1481909d828b3d5a44550a |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a5fd8481909433e923c5e24e55 |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 27, 2026, 8:28 a.m.