Triple
T7323378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Church |
E168806
|
entity |
| Predicate | inscriptionOnTower |
P23382
|
FINISHED |
| Object | Ein feste Burg ist unser Gott |
—
|
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: Ein feste Burg ist unser Gott | Statement: [Castle Church, inscriptionOnTower, Ein feste Burg ist unser Gott]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionOnTower Context triple: [Castle Church, inscriptionOnTower, Ein feste Burg ist unser Gott]
-
A.
inscriptionMaterial
Indicates the material substance on which an inscription is made or carved.
-
B.
inscriptionLocation
chosen
Indicates the place or surface on which an inscription is written or engraved.
-
C.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
-
D.
inscriptionFeature
Indicates that one entity bears or contains an inscribed element or marking that is treated as a notable feature in relation to another entity.
-
E.
inscriptionType
Indicates the specific kind or category of inscription associated with an entity (e.g., dedicatory, funerary, commemorative).
- 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_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f046b93c8190a80dd48ee409ec5d |
completed | March 27, 2026, 9:01 p.m. |
| PD | Predicate disambiguation | batch_69c6e77230048190b2c29ca6b3a65b8e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:03 p.m.