Triple
T34308538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Камен мост |
E880377
|
entity |
| Predicate | състояние |
P127
|
FINISHED |
| Object | запазен и реконструиран |
—
|
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: запазен и реконструиран | Statement: [Камен мост, състояние, запазен и реконструиран]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: състояние Context triple: [Камен мост, състояние, запазен и реконструиран]
-
A.
status
chosen
Indicates the current condition, state, or standing of an entity within a given context.
-
B.
inState
Indicates that an entity is currently located within or belongs to a particular state or condition.
-
C.
deFactoStatus
Indicates that one entity holds a role, position, or status in practice or by custom, even if it is not formally or legally recognized.
-
D.
principalState
Indicates that an entity serves as the primary or main state associated with another entity or context.
-
E.
secondaryState
Indicates that an entity is in a subordinate or less primary condition, status, or mode relative to its main or primary state.
- 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_69f349b8bb6c8190ad12a7957a574f04 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f717836f0c8190b4a397bbac37dd09 |
completed | May 3, 2026, 9:38 a.m. |
| PD | Predicate disambiguation | batch_69f7127a2ff08190b77d00963c9df621 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:57 a.m.