Triple
T28774579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kantakouzenos |
E726498
|
entity |
| Predicate | usedAsDynasticName |
P126784
|
FINISHED |
| Object | John VI Kantakouzenos |
—
|
NE NERFINISHED |
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: John VI Kantakouzenos | Statement: [Kantakouzenos, usedAsDynasticName, John VI Kantakouzenos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsDynasticName Context triple: [Kantakouzenos, usedAsDynasticName, John VI Kantakouzenos]
-
A.
dynasticUse
chosen
Indicates the use of something (such as a name, title, symbol, or resource) in a way that is tied to or characteristic of a particular dynasty or ruling family.
-
B.
dynasticNameDerivedFrom
Indicates that a dynastic name is derived from, or based on, another name, title, or source.
-
C.
usedAsRoyalNameOn
Indicates that something served as a royal name or title during a specified time or in a specified context.
-
D.
dynasticNameChangedTo
Indicates that an entity’s dynastic name was replaced by or transitioned into a new dynastic name.
-
E.
dynasticOrigin
Indicates the historical dynasty or ruling family from which an entity originates or descends.
- 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_69f03199997c8190b6ae43fb19312443 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 28, 2026, 6:17 a.m.