Triple
T37273284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trabzon Castle |
E924571
|
entity |
| Predicate | survivingElementsDateFrom |
P181824
|
FINISHED |
| Object | Byzantine period |
—
|
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: Byzantine period | Statement: [Trabzon Castle, survivingElementsDateFrom, Byzantine period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivingElementsDateFrom Context triple: [Trabzon Castle, survivingElementsDateFrom, Byzantine period]
-
A.
mayDateFrom
Indicates that one entity is permitted or allowed to go on a date with another entity.
-
B.
arisesFromDate
chosen
Indicates that something originates, begins, or comes into effect starting from a specified date.
-
C.
startDate
Indicates the point in time when an event, state, or relationship begins.
-
D.
dateOf
Indicates that one entity specifies the calendar date associated with another entity, such as when it occurred, was created, or is scheduled.
-
E.
createdBetween
Indicates that something was created within a specified start and end time or date range.
- 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_69f76eacdd8c819094080d3991e6d37c |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb78cbef988190b8f79d946b46e6b2 |
completed | May 6, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9ac5a08190b24ef308963fc52b |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:15 p.m.