Triple
T23222950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sverre Magnus |
E580941
|
entity |
| Predicate | positionInSuccessionToNorwegianThrone |
P129323
|
FINISHED |
| Object | third |
—
|
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: third | Statement: [Sverre Magnus, positionInSuccessionToNorwegianThrone, third]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInSuccessionToNorwegianThrone Context triple: [Sverre Magnus, positionInSuccessionToNorwegianThrone, third]
-
A.
successorAsKingOfNorway
Indicates that one person becomes the next king of Norway following another person in the royal succession.
-
B.
positionInLineOfSuccessionToThrone
chosen
Indicates the ordinal place an individual holds in the ordered sequence of heirs eligible to inherit a throne.
-
C.
isNextInLineOfSuccessionTo
Indicates that one entity is the immediate heir or successor designated to take over a position, title, or role when the current holder can no longer occupy it.
-
D.
successorAsKingOfDenmark
Indicates that one person becomes the next king of Denmark following another person in the royal succession.
-
E.
successorAsPrinceOfOrange
Indicates that one entity becomes the next holder of the title "Prince of Orange" after 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922a452c81909b48df157643f6bd |
completed | April 29, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:08 p.m.