Triple
T30063167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King of Georgia |
E763949
|
entity |
| Predicate | typicallyFromDynasty |
P204192
|
FINISHED |
| Object | Bagrationi dynasty |
E106774
|
NE 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: Bagrationi dynasty | Statement: [King of Georgia, typicallyFromDynasty, Bagrationi dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyFromDynasty Context triple: [King of Georgia, typicallyFromDynasty, Bagrationi dynasty]
-
A.
basedOnDynasty
Indicates that something is derived from, influenced by, or established on the foundation of a particular dynasty.
-
B.
nativeDynasty
Indicates that a dynasty is indigenous to, or originally from, the place or polity it rules or is associated with.
-
C.
dynastyProvided
Indicates that a particular dynasty supplied, supported, or was responsible for providing something to another entity or context.
-
D.
formedDynasty
Indicates that an entity established or created a ruling dynasty.
-
E.
builtDynastyAround
Indicates establishing and sustaining a long-term, dominant success or legacy centered on a particular person, group, or core element.
- F. None of above. chosen
Provenance (5 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_69f2247221388190a13a22c47094a0ef |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a03460f3a8c8190ae3f4cd69e0e54d9 |
completed | May 12, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a27324ec51481909eeba7de2693830e |
completed | June 8, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_6a0345810b3481908aec06ab2b712e12 |
completed | May 12, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_6a03460e44cc8190b1ac3e8ac0840a52 |
completed | May 12, 2026, 3:23 p.m. |
Created at: April 29, 2026, 6:58 p.m.