Triple
T2007358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISO 2108 |
E43615
|
entity |
| Predicate | defines |
P264
|
FINISHED |
| Object | ISBN system |
E6851
|
NE 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: ISBN system | Statement: [ISO 2108, defines, ISBN system]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISBN system Context triple: [ISO 2108, defines, ISBN system]
-
A.
International Standard Book Number
chosen
The International Standard Book Number (ISBN) is a globally recognized numeric identifier assigned to books and similar publications to uniquely distinguish and catalog them.
-
B.
International Standard Serial Number
The International Standard Serial Number (ISSN) is an eight-digit code used worldwide to uniquely identify serial publications such as journals, magazines, and newspapers.
-
C.
Dewey Decimal Classification
Dewey Decimal Classification is a widely used library classification system that organizes knowledge into ten main subject classes, each subdivided into more specific numeric categories.
-
D.
International Standard Bibliographic Description
International Standard Bibliographic Description is an international set of rules for creating consistent and standardized bibliographic records for library and information resources.
-
E.
Digital Object Identifier system
The Digital Object Identifier system is a standardized framework for assigning persistent, unique alphanumeric identifiers to digital content such as scholarly articles, enabling reliable citation, discovery, and long-term access.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8999e108190a07daa01452a5dab |
completed | March 7, 2026, 5:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0ae12d708190bcfe91e3ab53f04e |
completed | March 8, 2026, 11:48 p.m. |
Created at: March 4, 2026, 7:37 p.m.