Triple
T23437267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King of Lotharingia |
E563497
|
entity |
| Predicate | overlordContext |
P47636
|
FINISHED |
| Object | Carolingian emperor |
—
|
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: Carolingian emperor | Statement: [King of Lotharingia, overlordContext, Carolingian emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overlordContext Context triple: [King of Lotharingia, overlordContext, Carolingian emperor]
-
A.
overlordDuringReign
Indicates that one entity served as the ruling overlord of another entity during a specified reign period.
-
B.
lordOf
chosen
Indicates that one entity holds lordship, authority, or dominion over another entity.
-
C.
titleOfOverlord
Indicates that one entity is the formal title or designation held by an overlord (a ruling or dominant authority) in relation to another entity.
-
D.
relationshipToOverlords
Indicates the nature or type of connection, role, or allegiance that an entity has in relation to its overlords.
-
E.
overlordClaimedBy
Indicates that one entity is claimed as an overlord or ruling authority by another 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_69e24553980c8190bb66a2ae0bdab125 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a5dcd4608190a543cc747e0daab8 |
completed | April 29, 2026, 6:31 a.m. |
| PD | Predicate disambiguation | batch_69f061f92da081908e7f1d0cd1e9b01c |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 5:50 p.m.