Triple
T5002012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgian–Seljuk wars |
E112394
|
entity |
| Predicate | peakOfConflict |
P28865
|
FINISHED |
| Object | reign of David IV of Georgia |
—
|
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: reign of David IV of Georgia | Statement: [Georgian–Seljuk wars, peakOfConflict, reign of David IV of Georgia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakOfConflict Context triple: [Georgian–Seljuk wars, peakOfConflict, reign of David IV of Georgia]
-
A.
conflictBelligerent
Indicates that an entity is a participating belligerent (e.g., a country, group, or force) in a specific conflict.
-
B.
settingOfConflict
Indicates the location or context in which a conflict between entities takes place.
-
C.
regionOfConflict
Indicates that a specified region is the location where a particular conflict or dispute takes place.
-
D.
conflictPeriod
chosen
Indicates the time span during which a particular conflict or dispute is occurring or in effect between the related entities.
-
E.
politicalConflict
Indicates a relationship where entities are engaged in opposing political positions, struggles, or disputes, often involving competition for power, influence, or policy outcomes.
- 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_69bd4433d0b08190877e83959ef40d81 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7472a1dc8190942f568a81fdd961 |
completed | March 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69bd714aee2481908fb0dd5fa2daf3a1 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:34 p.m.