Triple
T28594160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Wikibooks |
E723729
|
entity |
| Predicate | supportsPageHistory |
P198988
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Korean Wikibooks, supportsPageHistory, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsPageHistory Context triple: [Korean Wikibooks, supportsPageHistory, yes]
-
A.
supportsHistory
Indicates that one entity provides assistance, endorsement, or foundational backing to another entity’s historical context, development, or continuity.
-
B.
supportsHistoryModel
chosen
Indicates that one entity provides or enables a history-tracking or historical-state model for another entity or process.
-
C.
preservesHistoryOf
Indicates that one entity maintains, safeguards, or keeps a record of the historical information, context, or state of another entity.
-
D.
supportsPagination
Indicates that the subject provides or is compatible with dividing content or results into discrete pages that can be navigated sequentially.
-
E.
supportsPageFlipping
Indicates that one entity provides the capability for another entity to flip between pages, such as in a document or paginated interface.
- 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_6a01289f781481908f3788f8a719f2f4 |
completed | May 11, 2026, 12:53 a.m. |
| PD | Predicate disambiguation | batch_6a012823c7248190961e20be48dd6246 |
completed | May 11, 2026, 12:51 a.m. |
Created at: April 28, 2026, 4:21 a.m.