Triple
T476876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samoans |
E9080
|
entity |
| Predicate | governanceRole |
P11687
|
FINISHED |
| Object | matai (chief) |
—
|
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: matai (chief) | Statement: [Samoans, governanceRole, matai (chief)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governanceRole Context triple: [Samoans, governanceRole, matai (chief)]
-
A.
governanceModel
Indicates the type or structure of authority, decision-making, and control that defines how an entity is directed and overseen.
-
B.
roleInCouncil
Indicates that an entity holds a specific position or function within a council or governing body.
-
C.
organizationTypeGoverned
Indicates that one entity governs or has authoritative control over a specific type or category of organization.
-
D.
servesRole
chosen
Indicates that one entity performs, fulfills, or occupies a particular function, position, or responsibility in relation to another entity.
-
E.
governance
Indicates the relationship in which one entity exercises authority, control, or decision-making power over the policies, actions, or direction of another entity or 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_69a2e7ff81708190b0507a24a997232c |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f03cc63881908e75b457804cb858 |
completed | Feb. 28, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69a2edf017548190ae38ff3314a1ffa3 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.