Triple
T29826507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1990 Myanmar general election |
E757394
|
entity |
| Predicate | rulingBeforeElection |
P167644
|
FINISHED |
| Object | State Law and Order Restoration Council |
—
|
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: State Law and Order Restoration Council | Statement: [1990 Myanmar general election, rulingBeforeElection, State Law and Order Restoration Council]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rulingBeforeElection Context triple: [1990 Myanmar general election, rulingBeforeElection, State Law and Order Restoration Council]
-
A.
positionBeforeElection
Indicates that an entity held a particular position or office prior to a specified election.
-
B.
incumbentBeforeElection
Indicates that the subject was already holding the relevant office or position prior to the specified election.
-
C.
mainOppositionBeforeElection
Indicates that one political entity serves as the primary opposing force to another in the period leading up to an election.
-
D.
incumbentBeforeAndAfter
Indicates that the same officeholder remains in position both before and after a specified event or time interval.
-
E.
speakerBeforeElection
Indicates that the person served as a speaker or spokesperson prior to an election event.
- F. None of above. chosen
Provenance (4 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_69f22457c84c8190a6d9f56bc74082a9 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67598dff081908ff0ec79a48b55ec |
completed | May 2, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69f66bd123108190b451eb6e23842adb |
completed | May 2, 2026, 9:25 p.m. |
Created at: April 29, 2026, 5:32 p.m.