Triple
T15022123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgar-slayer |
E378110
|
entity |
| Predicate | earnedFor |
P29970
|
FINISHED |
| Object | military victories over the Bulgarian Empire |
—
|
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: military victories over the Bulgarian Empire | Statement: [Bulgar-slayer, earnedFor, military victories over the Bulgarian Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earnedFor Context triple: [Bulgar-slayer, earnedFor, military victories over the Bulgarian Empire]
-
A.
pointsEarnedFrom
Indicates the number of points that an entity has received as a result of another specified source, action, or event.
-
B.
gainedBy
chosen
Indicates that something comes to possess, obtain, or receive something else as a result of an action, process, or event.
-
C.
canBeEarnedBy
Indicates that something (such as a reward, status, or resource) is obtainable through the actions, efforts, or qualifications of a particular entity.
-
D.
rewardFulfilledFor
Indicates that a previously promised or expected reward has been delivered or satisfied for a particular entity.
-
E.
rewardForCompletion
Indicates that something is given as a benefit or compensation in return for successfully completing a task, activity, or objective.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded765462c819097f331c9b39c80e3 |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a67cbc481909c19c2de57de4eb7 |
completed | April 14, 2026, 7:50 p.m. |
Created at: April 10, 2026, 2:56 a.m.