Triple
T13146704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Samoa Fono |
E312356
|
entity |
| Predicate | usesLegislativeSessions |
P776
|
FINISHED |
| Object | regular sessions |
—
|
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: regular sessions | Statement: [American Samoa Fono, usesLegislativeSessions, regular sessions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesLegislativeSessions Context triple: [American Samoa Fono, usesLegislativeSessions, regular sessions]
-
A.
usesLegislativeSessionName
Indicates that an entity refers to or is associated with a specific legislative session by its official name.
-
B.
legislativeActivity
Indicates involvement in creating, debating, amending, or passing laws or related legislative measures.
-
C.
legislativeSession
chosen
Indicates that an entity is a formal meeting period of a legislative body during which it conducts its official business, such as debating and passing laws.
-
D.
legislativeAudience
Indicates that the subject is the intended legislative body or group of lawmakers to whom a proposal, document, or action is directed.
-
E.
hasLegislativeSessionCount
Indicates the number of legislative sessions associated with a given legislative body, term, or jurisdiction.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bbd1d088190b7c69f37fc6eeb64 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:10 p.m.