Triple
T8683186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bolnisi Sioni Cathedral |
E206087
|
entity |
| Predicate | inscriptionsDateFrom |
P33352
|
FINISHED |
| Object | 493 |
—
|
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: 493 | Statement: [Bolnisi Sioni Cathedral, inscriptionsDateFrom, 493]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionsDateFrom Context triple: [Bolnisi Sioni Cathedral, inscriptionsDateFrom, 493]
-
A.
firstInscriptionYear
Indicates the year in which an entity was first inscribed, recorded, or officially entered into a relevant register or list.
-
B.
chroniclesPeriodFrom
Indicates that something documents or records events starting from a specified point in time or historical period.
-
C.
inscriptionDating
chosen
Indicates the temporal period or specific date to which an inscription is assigned or attributed.
-
D.
inscriptionYearOfFirstElements
Indicates the year in which the first elements of something (such as a site, object, or collection) were officially inscribed or recorded in a designated register or list.
-
E.
earliestLongCountDateOnMonument
Indicates the earliest recorded Long Count calendar date that appears on a given monument.
- 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_69ca835379688190aa06b9d98e684d58 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4ae9da3c8190866e24970a7aeba3 |
completed | March 31, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69cc4567b5c881908d9ec5dcfc783fac |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:32 p.m.