Triple
T9055226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarakatsani |
E216979
|
entity |
| Predicate | socialCustoms |
P33136
|
FINISHED |
| Object | conservative customs |
—
|
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: conservative customs | Statement: [Sarakatsani, socialCustoms, conservative customs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: socialCustoms Context triple: [Sarakatsani, socialCustoms, conservative customs]
-
A.
socialCustom
chosen
Indicates a culturally shared, customary way of behaving or interacting that is expected or considered appropriate within a particular social group or context.
-
B.
socialCategory
Indicates that an entity belongs to, or is classified within, a particular social group, class, or category.
-
C.
socialBase
Indicates a foundational social relationship or structure that underlies or supports interactions between entities.
-
D.
custom
Indicates that something is specially created, configured, or tailored for a particular purpose, context, or user rather than being standard or generic.
-
E.
socialCenter
Indicates that a place functions as a primary gathering point or hub for social interaction and community activities.
- 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_69ca83d4425481909a319dab847724ec |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc7a7488188190b3dd6bc2f2377503 |
completed | April 1, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee6d83c819095d8ed0779aa8511 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:10 p.m.