Triple
T29034845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jabrayil |
E737829
|
entity |
| Predicate | wasRecapturedDuring |
P89143
|
FINISHED |
| Object | 2020 Nagorno-Karabakh war |
—
|
NE NERFINISHED |
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: 2020 Nagorno-Karabakh war | Statement: [Jabrayil, wasRecapturedDuring, 2020 Nagorno-Karabakh war]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasRecapturedDuring Context triple: [Jabrayil, wasRecapturedDuring, 2020 Nagorno-Karabakh war]
-
A.
wasRecapturedBy
Indicates that an entity which had previously escaped or been released was caught again by another entity.
-
B.
recapturedInConflict
chosen
Indicates that an entity was taken back or regained during a specific conflict or war after previously being lost or captured.
-
C.
recapturedUnder
Indicates that an entity was captured again while under a specific authority, condition, or legal framework.
-
D.
recapturedWithSupportFrom
Indicates that an entity was taken back or regained with the assistance, backing, or involvement of another party or resource.
-
E.
capturedInWar
Indicates that one entity was taken prisoner or seized by another entity as a result of armed conflict or wartime actions.
- 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_69f077efb3848190b41574e1670f6ae2 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6603be0cc8190ba34acec15092a98 |
completed | May 2, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 9:57 a.m.