Triple
T28774598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kantakouzenos |
E726498
|
entity |
| Predicate | producedCoEmperor |
P41257
|
FINISHED |
| Object | Matthew 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: Matthew Kantakouzenos | Statement: [Kantakouzenos, producedCoEmperor, Matthew Kantakouzenos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: producedCoEmperor Context triple: [Kantakouzenos, producedCoEmperor, Matthew Kantakouzenos]
-
A.
producedEmperor
chosen
Indicates that one entity brought about, created, or was responsible for the rise or existence of an emperor.
-
B.
coEmperorWith
Indicates that two individuals simultaneously share the position and authority of emperor within the same imperial system.
-
C.
producedEmpress
Indicates that one entity created, generated, or brought about the existence or status of an empress.
-
D.
eraOfEmperor
Indicates the historical time period during which a particular emperor held power or reigned.
-
E.
finalEmperorOf
Indicates that one entity is the last ruler to hold the imperial title over another entity (such as a state, dynasty, or empire).
- 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_69fb563aec448190875410fb1a3ed624 |
completed | May 6, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69fb35b9ede881908aaae93a215525df |
completed | May 6, 2026, 12:36 p.m. |
Created at: April 28, 2026, 6:17 a.m.