Triple
T28593693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bengali Wikipedia |
E723719
|
entity |
| Predicate | openToEditsFrom |
P164894
|
FINISHED |
| Object | registered users |
—
|
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: registered users | Statement: [Bengali Wikipedia, openToEditsFrom, registered users]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openToEditsFrom Context triple: [Bengali Wikipedia, openToEditsFrom, registered users]
-
A.
openedAs
Indicates that one entity began operating, functioning, or being available to the public under the form, name, or role of another entity.
-
B.
openedIn
Indicates that an entity (such as a business, event, or institution) began operating or was inaugurated in a specific time period or location.
-
C.
openedFrom
Indicates that one entity was initiated, accessed, or launched as a result of an action performed within another entity.
-
D.
openedToReplace
Indicates that one entity was opened for the purpose of replacing something within or associated with it.
-
E.
opens
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
- 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f652a3a8208190a4fdd66f34138bd2 |
completed | May 2, 2026, 7:38 p.m. |
Created at: April 28, 2026, 4:21 a.m.