Triple
T23708476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ternopil Castle |
E585794
|
entity |
| Predicate | oneOfThe |
P35467
|
FINISHED |
| Object | oldest architectural monuments in Ternopil region |
—
|
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: oldest architectural monuments in Ternopil region | Statement: [Ternopil Castle, oneOfThe, oldest architectural monuments in Ternopil region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oneOfThe Context triple: [Ternopil Castle, oneOfThe, oldest architectural monuments in Ternopil region]
-
A.
oneOfFew
Indicates that the subject is one member of a small, limited set of entities that share a specified property or role.
-
B.
oneOfFewIn
chosen
Indicates that an entity is one among a small, limited number of entities that are in or belong to a specified set, group, or context.
-
C.
oneOfNine
Indicates that the subject is exactly one member of a specific group or set containing nine distinct options.
-
D.
oneOfWorlds
Indicates that an entity is a member of, or belongs to, a specified set or collection of possible worlds.
-
E.
oneOfCasesIn
Indicates that an entity is one specific member of a defined set or collection of possible cases.
- 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_69e24905f77881908194d645676acd60 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b775a4288190bbee7bd4b5bbcd75 |
completed | April 29, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 6:53 p.m.