Triple
T31530261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Campaigns against Great Moravia |
E804456
|
entity |
| Predicate | sovereignOfAttacker |
P43419
|
FINISHED |
| Object | Arnulf of Carinthia |
—
|
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: Arnulf of Carinthia | Statement: [Campaigns against Great Moravia, sovereignOfAttacker, Arnulf of Carinthia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sovereignOfAttacker Context triple: [Campaigns against Great Moravia, sovereignOfAttacker, Arnulf of Carinthia]
-
A.
countryAttacker
Indicates that one country is the aggressor or initiator of an attack against another country.
-
B.
sovereigntyHolder
Indicates which entity possesses ultimate governing authority or sovereign control over another entity or territory.
-
C.
enemyNation
Indicates that one nation is considered a hostile or adversarial state in relation to another nation.
-
D.
sovereignInvolved
chosen
Indicates that a sovereign authority (such as a monarch or state) is directly involved in, participates in, or is otherwise a key party to the referenced action or relationship.
-
E.
countryOfDefender
Indicates the country to which the defending party or entity in a conflict, dispute, or legal case belongs.
- 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_69f348d03ef88190a2b73d7b94b9e02d |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 30, 2026, 10 p.m.