Triple
T28055101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jorjadze family |
E708941
|
entity |
| Predicate | hasSurnameInGeorgian |
P16880
|
FINISHED |
| Object | ჯორჯაძე |
—
|
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: ჯორჯაძე | Statement: [Jorjadze family, hasSurnameInGeorgian, ჯორჯაძე]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurnameInGeorgian Context triple: [Jorjadze family, hasSurnameInGeorgian, ჯორჯაძე]
-
A.
GeorgianName
chosen
Indicates that an entity has a name that is in the Georgian language or follows Georgian naming conventions.
-
B.
hasSurnameEthymology
Indicates that an entity’s surname originates from, or is derived based on, a specified source, language, or etymological root.
-
C.
hasBaseSurname
Indicates that an entity’s surname is derived from, or fundamentally corresponds to, a specified base or canonical surname.
-
D.
hasCharacterWithSurname
Indicates that an entity (such as a work or story) includes at least one character whose surname matches the specified name.
-
E.
hasSeptSurname
Indicates that an entity bears a surname associated with a particular sept (a family subgroup or clan division).
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: April 27, 2026, 8:36 p.m.