Triple
T16736149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hadrut |
E406722
|
entity |
| Predicate | conflictOutcome2020 |
P21116
|
FINISHED |
| Object | shifted control from Armenian to Azerbaijani side |
—
|
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: shifted control from Armenian to Azerbaijani side | Statement: [Hadrut, conflictOutcome2020, shifted control from Armenian to Azerbaijani side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictOutcome2020 Context triple: [Hadrut, conflictOutcome2020, shifted control from Armenian to Azerbaijani side]
-
A.
partOfConflictOutcome
Indicates that one entity represents a specific component or aspect of the overall outcome of a conflict involving another entity.
-
B.
conflictEndYear
Indicates the calendar year in which a particular conflict, dispute, or war came to an end.
-
C.
concludedWar
Indicates that a war or armed conflict between entities has come to an end, typically through victory, surrender, or formal agreement.
-
D.
conflictResult
chosen
Indicates the outcome or consequence that arises from a particular conflict between entities.
-
E.
conflictCountry
Indicates that there is an armed conflict or war involving the referenced country as a participant.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e39c3a86848190a03f243dd1bdb899 |
completed | April 18, 2026, 2:59 p.m. |
| PD | Predicate disambiguation | batch_69e319c807788190901250ab6e0ca55f |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:20 a.m.