Triple
T16549486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Levounion |
E402030
|
entity |
| Predicate | impactOnPechenegs |
P124011
|
FINISHED |
| Object | destruction of Pecheneg military power |
—
|
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: destruction of Pecheneg military power | Statement: [Battle of Levounion, impactOnPechenegs, destruction of Pecheneg military power]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactOnPechenegs Context triple: [Battle of Levounion, impactOnPechenegs, destruction of Pecheneg military power]
-
A.
effectOnCossacks
Indicates the impact or consequences that something has on Cossacks as a group.
-
B.
effectOnSmolensk
Indicates the impact or consequences that something has on Smolensk.
-
C.
impactOnConstantinople
Indicates a relationship where one entity has an effect, influence, or consequence specifically on the city of Constantinople.
-
D.
effectOnRussia
Indicates the impact or consequences that something has on Russia.
-
E.
opponentInBattleOfLechfeld
Indicates that two entities were opposing sides against each other in the Battle of Lechfeld.
- F. None of above. chosen
Provenance (4 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_69d88384bc30819084229e7dcdc39a41 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e34fc323a88190b5c2a34de0a3c7f0 |
completed | April 18, 2026, 9:32 a.m. |
| PD | Predicate disambiguation | batch_69e2969fab208190ad64164d24748c45 |
completed | April 17, 2026, 8:22 p.m. |
| PDg | Predicate description generation | batch_69e2d7f97e548190a474691a152bd8e8 |
completed | April 18, 2026, 1:01 a.m. |
Created at: April 10, 2026, 5:15 a.m.