Triple
T18837820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2023 Madhya Pradesh Legislative Assembly election |
E460709
|
entity |
| Predicate | party1SeatChange |
P73160
|
FINISHED |
| Object | +36 |
—
|
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: +36 | Statement: [2023 Madhya Pradesh Legislative Assembly election, party1SeatChange, +36]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: party1SeatChange Context triple: [2023 Madhya Pradesh Legislative Assembly election, party1SeatChange, +36]
-
A.
secondPartySeatChange
Indicates that the second party’s assigned seat has been changed from one seat to another.
-
B.
thirdPartySeatChange
Indicates that a passenger’s seat assignment is changed by someone other than the passenger or the operating carrier (i.e., by a third party).
-
C.
snpNetSeatChange
Indicates a change in the number of seats held by a political party or group in a legislative body between two points in time.
-
D.
AllianceSeatChange
Indicates a change in a party’s or member’s seat allocation resulting from forming, joining, leaving, or reconfiguring a political alliance.
-
E.
winningPartySeatChange
chosen
Indicates the change in the number of seats held by the winning party compared to a previous election or reference point.
- 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_69d8dcfa11e4819090ab1ef5bdcd2b2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99f443881909516a82208fd0178 |
completed | April 20, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69e48d1e7dac81909ea1e758c87773c5 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:56 a.m.