Triple
T23646750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malamir of Bulgaria |
E584056
|
entity |
| Predicate | successorPossiblyRelatedAs |
P153019
|
FINISHED |
| Object | uncle of Presian I of Bulgaria |
—
|
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: uncle of Presian I of Bulgaria | Statement: [Malamir of Bulgaria, successorPossiblyRelatedAs, uncle of Presian I of Bulgaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorPossiblyRelatedAs Context triple: [Malamir of Bulgaria, successorPossiblyRelatedAs, uncle of Presian I of Bulgaria]
-
A.
successorRelations
Indicates that one entity directly follows or succeeds another in an ordered sequence or progression.
-
B.
successionRelation
Indicates that one entity follows another in an ordered sequence, such as in time, position, or rank.
-
C.
successorRelationship
Indicates a relationship where one entity directly follows or replaces another in a sequence, order, or role.
-
D.
possibleSuccessorPeoples
Indicates that one group of people is a potential successor or replacement for another group in a given context or role.
-
E.
successorRelationCertainty
Indicates the degree of confidence or assurance that one entity is the successor of another in a given succession relationship.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b28571bc8190b3f7275068d19320 |
completed | April 29, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f1233300bc8190ac1639bdca1d7d99 |
completed | April 28, 2026, 9:14 p.m. |
Created at: April 17, 2026, 6:48 p.m.