Triple
T20443202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan of Rûm |
E501447
|
entity |
| Predicate | successorTitleInRegion |
P97833
|
FINISHED |
| Object | bey titles of Anatolian beyliks |
—
|
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: bey titles of Anatolian beyliks | Statement: [Sultan of Rûm, successorTitleInRegion, bey titles of Anatolian beyliks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorTitleInRegion Context triple: [Sultan of Rûm, successorTitleInRegion, bey titles of Anatolian beyliks]
-
A.
successorTitle
Indicates the title or position that directly follows and replaces a previous one in a sequence or succession.
-
B.
successorTitleLocation
chosen
Indicates the location or context in which a successor’s title or position is held or applies.
-
C.
successorTitleContext
Indicates the contextual circumstances or framework under which one title succeeds another.
-
D.
successorInRegion
Indicates that one entity directly follows or replaces another within a specified region or jurisdiction.
-
E.
successorTitleIntegratedInto
Indicates that the title of a successor entity has been merged into and is now part of another title or entity.
- 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68cfa7dd08190883a37e3480b152c |
completed | April 20, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69e5766df0008190a73c4f613c29678f |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:32 a.m.