Triple
T33287547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Voices of the left |
E852219
|
entity |
| Predicate | describesEditorialStance |
P8702
|
FINISHED |
| Object | left-wing |
—
|
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: left-wing | Statement: [Voices of the left, describesEditorialStance, left-wing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: describesEditorialStance Context triple: [Voices of the left, describesEditorialStance, left-wing]
-
A.
editorialStance
chosen
Indicates the position, viewpoint, or bias an editor or publication adopts toward a subject, issue, or entity.
-
B.
hasAuthorialStance
Indicates that an entity expresses, embodies, or is associated with a particular author’s viewpoint, attitude, or perspective toward its subject matter.
-
C.
editorialNote
Indicates that there is an accompanying editorial comment or clarification about the related content, typically added by an editor rather than the original author.
-
D.
editorialRole
Indicates that one entity holds an editorial position or responsibility in relation to another entity, such as a publication, work, or organization.
-
E.
editorialStandard
Indicates that one entity defines, follows, or enforces a particular set of editorial rules, guidelines, or quality criteria in relation to another entity or content.
- 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_69f349660ff48190a4568803d0b89941 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fbc9d1dba881908c399b8e1dc13ce2 |
completed | May 6, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 1, 2026, 1:32 a.m.