Triple
T31858802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constantinopolitan civil aristocracy |
E813266
|
entity |
| Predicate | derivesPowerFrom |
P173782
|
FINISHED |
| Object | imperial service |
—
|
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: imperial service | Statement: [Constantinopolitan civil aristocracy, derivesPowerFrom, imperial service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: derivesPowerFrom Context triple: [Constantinopolitan civil aristocracy, derivesPowerFrom, imperial service]
-
A.
powerHarnessedBy
Indicates that a source of power or energy is captured, controlled, or utilized by a particular agent or system.
-
B.
usesEnergyFrom
Indicates that one entity derives or consumes energy originating from another entity as its source.
-
C.
usesPowerFor
Indicates that one entity applies or exploits a particular power, energy, or capability for a specific purpose or activity.
-
D.
modeOfPower
Indicates the type or method of power or energy by which an entity operates or is driven.
-
E.
propulsionSource
Indicates the mechanism or system that provides thrust or driving force for an object’s movement.
- 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_69f348ebf32881908d9439646933dc76 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ba1733408190af579d93a7946508 |
completed | May 3, 2026, 2:59 a.m. |
| PD | Predicate disambiguation | batch_69f6b6293188819080d5041ca0adb969 |
completed | May 3, 2026, 2:42 a.m. |
| PDg | Predicate description generation | batch_69f6b960ca4081909a77690c2b122f5e |
completed | May 3, 2026, 2:56 a.m. |
Created at: April 30, 2026, 11:52 p.m.