Triple
T11063668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medea Benjamin |
E261567
|
entity |
| Predicate | criticOf |
P56725
|
FINISHED |
| Object | U.S. drone warfare |
—
|
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: U.S. drone warfare | Statement: [Medea Benjamin, criticOf, U.S. drone warfare]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criticOf Context triple: [Medea Benjamin, criticOf, U.S. drone warfare]
-
A.
criticizedFor
Indicates that one entity expresses disapproval or negative judgment of another entity specifically because of a particular action, quality, or outcome.
-
B.
criticizedConstruct
Indicates that one entity expressed disapproval or negative judgment about another entity’s constructed work, idea, or creation.
-
C.
criticizesSource
Indicates that one entity expresses disapproval of, or negative judgment about, the content, behavior, or credibility of another entity that is treated as a source.
-
D.
criticObjective
chosen
Indicates that an entity serves as the target or focus of a critic’s evaluation, commentary, or judgment.
-
E.
criticizesPosition
Indicates that one entity expresses disapproval of, challenges, or points out flaws in another entity’s stance, viewpoint, or argument.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798ed07f88190bf501d9f63386ada |
completed | April 9, 2026, 12:17 p.m. |
| PD | Predicate disambiguation | batch_69d74411d9e881908c0eeafa0f38e4b6 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.