Triple
T29008850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | President of the Nagorno-Karabakh Republic |
E736507
|
entity |
| Predicate | officeSuspended |
P41676
|
FINISHED |
| Object | 2023 |
—
|
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: 2023 | Statement: [President of the Nagorno-Karabakh Republic, officeSuspended, 2023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeSuspended Context triple: [President of the Nagorno-Karabakh Republic, officeSuspended, 2023]
-
A.
officeSuspendedUnder
chosen
Indicates that an individual’s official position or duties are temporarily halted under the authority or jurisdiction of a specified entity or rule.
-
B.
workSuspendedOn
Indicates that work on an activity, task, or project has been temporarily halted or put on hold at a specific time or under certain conditions.
-
C.
workSuspensionRequired
Indicates that a temporary halt or suspension of work activities is mandated under certain conditions.
-
D.
workSuspendedOnFirstDay
Indicates that the work or project was halted or put on hold on its very first day of activity.
-
E.
officeState
Indicates the current operational or functional status of an office (e.g., open, closed, active, inactive) at a given time.
- 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_69f077eb81e88190ad9ff62cbb9f555e |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fdbc5ef46c8190bbcfb9798f4615b7 |
completed | May 8, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69fdbb270338819082ce3f73903e884f |
completed | May 8, 2026, 10:29 a.m. |
Created at: April 28, 2026, 9:40 a.m.