Triple
T27979758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The In Campaign |
E706585
|
entity |
| Predicate | mainOpposingPosition |
P50211
|
FINISHED |
| Object | Brexit |
—
|
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: Brexit | Statement: [The In Campaign, mainOpposingPosition, Brexit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainOpposingPosition Context triple: [The In Campaign, mainOpposingPosition, Brexit]
-
A.
positionOpposed
Indicates that two entities hold positions or stances that are in direct conflict or opposition to each other.
-
B.
mainOppositionCondition
Indicates the primary circumstance or factor that defines or triggers the main opposition between parties or positions.
-
C.
theoryOpposed
Indicates that one theory stands in opposition to, or conflicts with, another theory.
-
D.
primaryOpposition
chosen
Indicates the main or most significant opposing relationship between two entities, such as their chief rival, counterforce, or contrasting position.
-
E.
positionAffirmedByOpponents
Indicates that a particular stance or claim is confirmed, validated, or supported by those who are typically opposed to it.
- 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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63b6802d081908721f6bb9c0d8180 |
completed | May 2, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 7:43 p.m.