Triple
T17382982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawiye clans |
E422614
|
entity |
| Predicate | subBranchOf |
P34378
|
FINISHED |
| Object | Somali clan system |
—
|
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: Somali clan system | Statement: [Hawiye clans, subBranchOf, Somali clan system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subBranchOf Context triple: [Hawiye clans, subBranchOf, Somali clan system]
-
A.
subbranchOf
chosen
Indicates that one entity is a subordinate or secondary branch derived from, and structurally dependent on, another entity.
-
B.
subclassOf
Indicates that one class is a more specific type of another class, inheriting its characteristics as a subset of it.
-
C.
isUniqueBranchOf
Indicates that one branch is the sole or distinct sub-branch associated with a particular parent entity or structure.
-
D.
branchesFrom
Indicates that one entity originates or diverges from another as a subordinate or offshoot path, structure, or lineage.
-
E.
siblingBranch
Indicates that two branches share the same immediate parent node in a hierarchical structure, making them parallel or peer branches.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a87d9948190986021f1fb5a4e00 |
completed | April 19, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69e3b02ac8688190a7182f1b2151d721 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:45 a.m.