Triple
T15324647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Electoral constituencies of Nepal |
E366377
|
entity |
| Predicate | lastRedelimitation |
P46007
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [Electoral constituencies of Nepal, lastRedelimitation, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastRedelimitation Context triple: [Electoral constituencies of Nepal, lastRedelimitation, 2017]
-
A.
lastDelimitationYear
chosen
Indicates the year in which the most recent boundary or delimitation of the entity was officially established or updated.
-
B.
currentDelimitationFrom
Indicates that one entity currently defines or establishes the boundary or extent of another entity.
-
C.
laterFlag
Indicates that one event, state, or action occurs at a time later than another referenced event, state, or action.
-
D.
lastReform
Indicates the most recent reform or change that was applied to an entity, typically linking the entity to its latest reform event or version.
-
E.
lastUnitToLeave
Indicates that the referenced unit is the final one to depart from a given location, group, or context.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd5ce0c819093c9a14de549dff6 |
completed | April 16, 2026, 1:39 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:16 a.m.