Triple
T30703922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Kihanja |
E781699
|
entity |
| Predicate | hasSocietalOrganization |
P58264
|
FINISHED |
| Object | clan-based hierarchy |
—
|
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 hierarchy | Statement: [Kingdom of Kihanja, hasSocietalOrganization, clan-based hierarchy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSocietalOrganization Context triple: [Kingdom of Kihanja, hasSocietalOrganization, clan-based hierarchy]
-
A.
societalOrganization
chosen
Indicates how a society is structured and organized in terms of its institutions, roles, and social relationships.
-
B.
hasParentSociety
Indicates that an entity is organizationally or structurally subordinate to, and part of, a larger parent society.
-
C.
hasCivicOrganization
Indicates that an entity is associated with, supported by, or contains a civic organization, such as a community, volunteer, or public-interest group.
-
D.
hasOrganizations
Indicates that an entity is associated with, linked to, or includes one or more organizations.
-
E.
hasStudentOrganization
Indicates that an entity (such as an institution or department) is associated with or hosts a particular student organization.
- 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_69f224abfcf081909492e64d3cc35262 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 29, 2026, 8:34 p.m.