Triple
T8380076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wikisource |
E197665
|
entity |
| Predicate | hasFormerName |
P65
|
FINISHED |
| Object | Project Sourceberg |
E197665
|
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: Project Sourceberg | Statement: [Wikisource, hasFormerName, Project Sourceberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Project Sourceberg Context triple: [Wikisource, hasFormerName, Project Sourceberg]
-
A.
Project Sourceberg
chosen
Project Sourceberg was the original name for Wikisource, a Wikimedia project that provides a free online library of source texts and public domain documents.
-
B.
CodePlex
CodePlex was a now-defunct open-source project hosting website created by Microsoft that served as a central platform for collaborative software development.
-
C.
Project Jupyter
Project Jupyter is an open-source initiative that develops interactive computing tools and standards, most notably the Jupyter ecosystem for creating and sharing computational notebooks across multiple programming languages.
-
D.
Meta Open Source team
The Meta Open Source team is a group at Meta responsible for developing, maintaining, and stewarding key open-source projects and communities.
-
E.
Fossil SCM
Fossil SCM is a distributed software configuration management system that integrates version control, bug tracking, and a wiki into a single self-contained platform.
- 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_69ca82f64c188190af4e1608036b865d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80c57080819097eef2b7e46eaaee |
completed | March 31, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde803ac088190ae185ef444c9c7b9 |
completed | April 2, 2026, 3:52 a.m. |
Created at: March 30, 2026, 6:02 p.m.