Triple
T29485562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2022 Manipur Legislative Assembly election |
E747908
|
entity |
| Predicate | alliance1 |
P600
|
FINISHED |
| Object | National Democratic Alliance |
—
|
NE NERFINISHED |
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: National Democratic Alliance | Statement: [2022 Manipur Legislative Assembly election, alliance1, National Democratic Alliance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alliance1 Context triple: [2022 Manipur Legislative Assembly election, alliance1, National Democratic Alliance]
-
A.
alliance
chosen
Indicates a formal cooperative relationship between entities who agree to support each other in shared goals or interests.
-
B.
allianceType
Indicates the specific kind or category of alliance relationship that exists between entities.
-
C.
allianceUse
Indicates that one party makes use of, benefits from, or leverages an alliance or allied relationship with another party.
-
D.
allianceMember
Indicates that an entity is a member or participant in a specific alliance or coalition.
-
E.
allianceName
Indicates the designated name or title assigned to an alliance between entities.
- 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_69f0bd43ba30819095eb1cfc3adf525c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c05947c8190b34739a0a7c0201f |
completed | May 2, 2026, 9:26 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:08 p.m.