Triple
T35616042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruprecht, Count Palatine of the Rhine |
E1029167
|
entity |
| Predicate | region of rule |
P15936
|
FINISHED |
| Object | Rhine |
—
|
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: Rhine | Statement: [Ruprecht, Count Palatine of the Rhine, region of rule, Rhine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: region of rule Context triple: [Ruprecht, Count Palatine of the Rhine, region of rule, Rhine]
-
A.
regionRuled
chosen
Indicates that a particular region is governed or controlled by a specified ruler or authority.
-
B.
regionRuledLocatedIn
Indicates that the region governed or ruled by an entity is geographically located within a specified larger area or place.
-
C.
ruledFromRegion
Indicates that a ruling authority exercised control or governance over a domain while being based in or operating from a specific region.
-
D.
dstRuleRegion
Indicates that a rule applies specifically to, or is associated with, a particular destination region.
-
E.
isRegionOf
Indicates that one entity is a geographic or administrative region belonging to, contained within, or associated with 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_69f76e0709408190bbe322bf1707ef6b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ffcf46fd688190907fd1ceb499a8d1 |
completed | May 10, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69ffccde2a8c81908e055e74077dbd19 |
completed | May 10, 2026, 12:10 a.m. |
Created at: May 3, 2026, 4:05 p.m.