Triple
T19723228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donmeh |
E473660
|
entity |
| Predicate | organizationalDivision |
P14872
|
FINISHED |
| Object | Karakaş subgroup |
—
|
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: Karakaş subgroup | Statement: [Donmeh, organizationalDivision, Karakaş subgroup]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: organizationalDivision Context triple: [Donmeh, organizationalDivision, Karakaş subgroup]
-
A.
companyDivision
Indicates that one entity is a division, branch, or subordinate business unit within the organizational structure of another company entity.
-
B.
divisionOrStructure
chosen
Indicates a relationship where one entity is an internal division, department, or structural subunit that is organizationally contained within another entity.
-
C.
dividesOrganizationInto
Indicates that an entity structures or partitions an organization into distinct subunits, sections, or divisions.
-
D.
workDivision
Indicates how a task, responsibility, or set of activities is split and allocated among multiple entities.
-
E.
relatedDivision
Indicates that there is an organizational or structural association between two divisions, such as being counterparts, partners, or otherwise linked within a broader entity.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649f64984819097882c44098b1643 |
completed | April 20, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69e5304a7aac8190ac13f75f0c008e45 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:46 p.m.