Triple
T35971068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Изборская крепость |
E1040285
|
entity |
| Predicate | перестроенаВеке |
P24909
|
FINISHED |
| Object | XIV век |
—
|
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: XIV век | Statement: [Изборская крепость, перестроенаВеке, XIV век]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: перестроенаВеке Context triple: [Изборская крепость, перестроенаВеке, XIV век]
-
A.
reconstructedEvery
Indicates that one entity has rebuilt or restored every instance of another entity completely.
-
B.
reconstructedAfter
Indicates that one entity has been rebuilt, restored, or reassembled following the occurrence or existence of another entity or event.
-
C.
reconstructedDuring
chosen
Indicates that an entity was rebuilt, restored, or significantly repaired within a specified time period or event.
-
D.
reconstructedIn
Indicates that something has been rebuilt, restored, or re-created within a particular context, location, or medium.
-
E.
reconstructedFor
Indicates that something has been rebuilt, restored, or re-created for the benefit, use, or purpose of another entity.
- 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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7acaec1508190a38f2ac9cc5383e7 |
completed | May 3, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f7ab75387c819091afc3c2128eb903 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:07 p.m.