Triple
T21972811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abaza people |
E542631
|
entity |
| Predicate | traditionalClanStructure |
P105710
|
FINISHED |
| Object | clan-based society |
—
|
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: clan-based society | Statement: [Abaza people, traditionalClanStructure, clan-based society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalClanStructure Context triple: [Abaza people, traditionalClanStructure, clan-based society]
-
A.
traditionalStructure
Indicates that something follows or embodies a customary, historically established form, pattern, or organizational framework.
-
B.
traditionalSocialUnit
Indicates that one entity functions as a customary or historically established basic social grouping or organizational unit in relation to another.
-
C.
clanStructureElement
Indicates a relationship where something functions as a structural component or defined part within a clan’s organizational hierarchy.
-
D.
clanPrinciple
Indicates a guiding rule, value, or norm that governs the behavior or organization of a clan.
-
E.
clanOrSocietySystem
chosen
Indicates a relationship where a group is organized or structured according to a particular clan or society system.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f124857dcc8190ab474cd8ab9c130a |
completed | April 28, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69e6f601f2188190893bcdde0cf58ad6 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 8:02 p.m.