Triple
T1590828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Nations General Assembly |
E34173
|
entity |
| Predicate | startsRegularSessionIn |
P1309
|
FINISHED |
| Object | September |
—
|
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: September | Statement: [United Nations General Assembly, startsRegularSessionIn, September]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startsRegularSessionIn Context triple: [United Nations General Assembly, startsRegularSessionIn, September]
-
A.
firstSessionStart
Indicates the point in time when an entity’s very first session or interaction begins.
-
B.
secondSessionStart
Indicates the point in time when a second or subsequent session begins.
-
C.
convenesRegularSession
chosen
Indicates that an entity formally brings together a group or body for its routine or scheduled meeting.
-
D.
instructionBegan
Indicates that an instructional process or teaching activity has started.
-
E.
startedActingOn
Indicates that one entity has begun to perform, execute, or apply an action, influence, or process upon another 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93aedd45c819085843ac843d640e8 |
completed | March 5, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69a907bdc19081908c84c5c0aa09e282 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.