Triple
T4445604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Alexander Nevsky Cathedral, Sofia |
E96276
|
entity |
| Predicate | cryptFunction |
P56554
|
FINISHED |
| Object | icon museum |
—
|
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: icon museum | Statement: [St. Alexander Nevsky Cathedral, Sofia, cryptFunction, icon museum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cryptFunction Context triple: [St. Alexander Nevsky Cathedral, Sofia, cryptFunction, icon museum]
-
A.
cryptDesigner
Indicates that an entity is the designer or creator responsible for planning or conceiving a particular crypt.
-
B.
cipherCategory
Indicates that one item is classified as a type or category of cipher to which the other item belongs.
-
C.
hasCrypt
Indicates that one entity possesses, contains, or is associated with a crypt belonging to or located within it.
-
D.
ciphertextExpansion
Indicates that applying the encryption process to the input increases its length, specifying how much the ciphertext expands relative to the original data.
-
E.
hashFunction
Indicates a relationship where an input value is transformed into a fixed-size output (hash) according to a specific deterministic hashing algorithm.
- F. None of above. chosen
Provenance (4 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_69b345415ba481908df738e7174448ba |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355d1eba08190899d0a3c1684ce4e |
completed | March 13, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69b34f62c180819097ced38da2052207 |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b35034cd248190bae09e9d090e13ec |
completed | March 12, 2026, 11:45 p.m. |
Created at: March 12, 2026, 11:32 p.m.