Triple
T38129281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | René Azaire |
E952171
|
entity |
| Predicate | treatsWorkers |
P159042
|
FINISHED |
| Object | harshly |
—
|
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: harshly | Statement: [René Azaire, treatsWorkers, harshly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatsWorkers Context triple: [René Azaire, treatsWorkers, harshly]
-
A.
involvesWorkers
Indicates that an event, process, or situation includes workers as active participants or affected parties.
-
B.
representsWorkersOf
Indicates a relationship where one entity denotes or stands for the workers associated with another entity.
-
C.
effectOnWorkers
chosen
Indicates the impact or consequences that something has on workers, such as changes to their conditions, well-being, or employment.
-
D.
includesTreatmentWorks
Indicates that something (such as a plan, project, or system) contains or incorporates specific treatment works or treatment facilities as part of it.
-
E.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
- 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_69f76f083548819082bd2bbf53c79e8e |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:21 p.m.