Triple
T28594732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serbian Wikipedia |
E723741
|
entity |
| Predicate | hasAboutPage |
P16909
|
FINISHED |
| Object | https://sr.wikipedia.org/wiki/Википедија:О_пројекту |
—
|
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: https://sr.wikipedia.org/wiki/Википедија:О_пројекту | Statement: [Serbian Wikipedia, hasAboutPage, https://sr.wikipedia.org/wiki/Википедија:О_пројекту]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAboutPage Context triple: [Serbian Wikipedia, hasAboutPage, https://sr.wikipedia.org/wiki/Википедија:О_пројекту]
-
A.
hasPolicyPage
Indicates that an entity maintains or is associated with a dedicated policy page, typically outlining rules, terms, or guidelines.
-
B.
hasPage
chosen
Indicates that one entity includes, is associated with, or is documented by a specific page (such as a web page or document page).
-
C.
hostsContentAbout
Indicates that one entity provides, contains, or makes available content whose subject or focus is another entity.
-
D.
hasCompanionWebsite
Indicates that something is associated with or supported by a dedicated companion website.
-
E.
hasFamousPage
Indicates that an entity is associated with a well-known or widely recognized page, such as on a website or platform.
- 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:21 a.m.