Triple
T993920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frederick the Wise |
E21451
|
entity |
| Predicate | refused |
P438
|
FINISHED |
| Object | offer to become Holy Roman 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: offer to become Holy Roman Emperor | Statement: [Frederick the Wise, refused, offer to become Holy Roman Emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refused Context triple: [Frederick the Wise, refused, offer to become Holy Roman Emperor]
-
A.
rejectedBy
chosen
Indicates that one entity has been refused, dismissed, or not accepted by another entity.
-
B.
rejectedJustification
Indicates that a proposed justification or reason offered in a context (e.g., argument, decision, or claim) has been evaluated and not accepted as valid or sufficient.
-
C.
rarelyRefused
Indicates that an action, request, or offer is almost always accepted and only infrequently declined.
-
D.
rejectedAward
Indicates that an entity refused to accept or declined an award that was offered or granted to it.
-
E.
rejectedClaim
Indicates that one party has refused to accept, approve, or validate a claim made by another party.
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4c5e16881908cd5f7ba2fcd5084 |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2af071c819086c374a16307dfe0 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.