Triple
T18246430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Satversme of Latvia |
E436963
|
entity |
| Predicate | suspensionStartDate |
P38380
|
FINISHED |
| Object | 1934-05-15 |
—
|
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: 1934-05-15 | Statement: [Satversme of Latvia, suspensionStartDate, 1934-05-15]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspensionStartDate Context triple: [Satversme of Latvia, suspensionStartDate, 1934-05-15]
-
A.
suspensionDate
chosen
Indicates the date on which an entity’s normal status, operation, or privileges are formally suspended.
-
B.
suspensionPeriod
Indicates the time span during which a right, service, or status is temporarily inactive or halted.
-
C.
suspendedFrom
Indicates that one entity is hanging or held up in the air by being attached to another supporting entity.
-
D.
suspendedAfter
Indicates that one entity is suspended or put on hold after the occurrence or completion of another entity or event.
-
E.
suspensionYear
Indicates the year in which a suspension (such as a ban, halt, or temporary discontinuation of activity) takes effect or is recorded.
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e7d49c8190b227a13b63615754 |
completed | April 19, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69e44fcdee748190bae6fb76e0cb22f3 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:33 a.m.