Triple
T13936591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cotton Library |
E335135
|
entity |
| Predicate | hasShelfmarkSystem |
P111854
|
FINISHED |
| Object | bust of Roman emperor |
—
|
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: bust of Roman emperor | Statement: [Cotton Library, hasShelfmarkSystem, bust of Roman emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShelfmarkSystem Context triple: [Cotton Library, hasShelfmarkSystem, bust of Roman emperor]
-
A.
hasDeweyDecimalClassification
Indicates that an item (such as a book or resource) is assigned a specific Dewey Decimal Classification number representing its subject area in a library system.
-
B.
hasBorrowingSystem
Indicates that an entity possesses or employs a system or mechanism for borrowing items, resources, or services.
-
C.
hasLibraryHoldings
Indicates that a library possesses or maintains specific items or collections within its holdings.
-
D.
hasBibliographicCategory
Indicates that an entity is associated with a specific bibliographic classification or category within a cataloging or documentation system.
-
E.
hasLccn
Indicates that an entity is associated with a specific Library of Congress Control Number (LCCN) as its unique identifier in the Library of Congress catalog.
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2cf42878819085146670d7b92605 |
completed | April 14, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69dbc873052c8190b33ff7f7c5a4e7ee |
completed | April 12, 2026, 4:29 p.m. |
| PDg | Predicate description generation | batch_69dcad0fc42c8190ada203febd57e851 |
completed | April 13, 2026, 8:45 a.m. |
Created at: April 9, 2026, 10:17 p.m.