Triple
T25946962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shipka Memorial Church |
E653864
|
entity |
| Predicate | cryptContains |
P5511
|
FINISHED |
| Object | ossuary with remains of Bulgarian soldiers |
—
|
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: ossuary with remains of Bulgarian soldiers | Statement: [Shipka Memorial Church, cryptContains, ossuary with remains of Bulgarian soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cryptContains Context triple: [Shipka Memorial Church, cryptContains, ossuary with remains of Bulgarian soldiers]
-
A.
cryptUse
Indicates that one entity uses, applies, or relies on a cryptographic method, key, or mechanism in relation to another entity or data.
-
B.
cryptFunction
Indicates a function or method that performs cryptographic processing, such as encrypting, decrypting, or otherwise transforming data using a cryptographic algorithm.
-
C.
hasCrypt
chosen
Indicates that one entity possesses, contains, or is associated with a crypt belonging to or located within it.
-
D.
cipherKey
Indicates that one entity serves as the cryptographic key used to encrypt or decrypt information associated with another entity.
-
E.
ciphertextType
Indicates the specific kind or format of ciphertext produced or used in an encryption process.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f60466a32c8190a73b55901951a9e1 |
completed | May 2, 2026, 2:04 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:43 a.m.