Triple
T36774833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Book (Röda boken) |
E908586
|
entity |
| Predicate | monarchDuringCompilation |
P163091
|
FINISHED |
| Object | John III of Sweden |
—
|
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 III of Sweden | Statement: [Red Book (Röda boken), monarchDuringCompilation, John III of Sweden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monarchDuringCompilation Context triple: [Red Book (Röda boken), monarchDuringCompilation, John III of Sweden]
-
A.
monarchDuringIssue
chosen
Indicates that a specified person was the reigning monarch at the time a particular item, event, or issue occurred or was produced.
-
B.
monarchUntil
Indicates that an entity served as monarch over another entity up to, but not beyond, a specified end time or event.
-
C.
monarchOnCreation
Indicates that an individual became the reigning monarch at the moment of a political entity’s creation or establishment.
-
D.
monarchIn
Indicates that a person serves as the ruling monarch of a specified country, state, or territory.
-
E.
monarchIs
Indicates that one entity serves as the ruling monarch (such as king, queen, or equivalent sovereign) of another entity, typically a state or territory.
- 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_69f76e798aa08190ace31098d1b13e9f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.