Triple
T5267215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samtavro Monastery |
E118966
|
entity |
| Predicate | originalConstructionDateApprox |
P13262
|
FINISHED |
| Object | 4th century |
—
|
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: 4th century | Statement: [Samtavro Monastery, originalConstructionDateApprox, 4th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalConstructionDateApprox Context triple: [Samtavro Monastery, originalConstructionDateApprox, 4th century]
-
A.
constructionDate
Indicates the date on which an entity (such as a building or structure) was constructed or completed.
-
B.
estimatedYearOfCreation
chosen
Indicates the year in which something is believed or approximated to have been created, rather than a precisely known creation year.
-
C.
yearBuilt
Indicates the specific year in which something (typically a structure or object) was constructed or completed.
-
D.
approximateDesignYear
Indicates the estimated or inferred year in which something was designed, rather than a precisely known design year.
-
E.
demolitionYearApprox
Indicates that an entity was demolished in or around a particular year, where the year is an approximate rather than an exact value.
- 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_69bd446a42c88190b7ecbef006561d55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77c71268819094f9f5203eed392d |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:51 p.m.