Triple
T5123764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fränkische Rezat |
E115534
|
entity |
| Predicate | joinsWith |
P1018
|
FINISHED |
| Object | Schwäbische Rezat at Georgensgmünd |
—
|
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: Schwäbische Rezat at Georgensgmünd | Statement: [Fränkische Rezat, joinsWith, Schwäbische Rezat at Georgensgmünd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: joinsWith Context triple: [Fränkische Rezat, joinsWith, Schwäbische Rezat at Georgensgmünd]
-
A.
joins
Indicates that one entity becomes a member or part of another entity, typically by entering into an organization, group, or association.
-
B.
joinsBefore
Indicates that one entity becomes a member or participant in a group, process, or activity earlier in time than another entity.
-
C.
joinedByInPart
Indicates that multiple entities are connected or associated together through a shared participation in a specific part or component of something.
-
D.
joinedPluralityBy
Indicates that multiple entities collectively became members or participants of the same group, organization, or event through a shared act of joining.
-
E.
hasJunctionWith
chosen
Indicates that one entity meets or intersects with another at a shared junction point.
- 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_69bd4442ade0819087b9461f892b206b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77aa68b88190a50dd736a72d2901 |
completed | March 20, 2026, 4:36 p.m. |
Created at: March 20, 2026, 1:42 p.m.