Triple
T27954007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Woodworking |
E703502
|
entity |
| Predicate | requiresSafetyPractice |
P20206
|
FINISHED |
| Object | eye protection |
—
|
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: eye protection | Statement: [Woodworking, requiresSafetyPractice, eye protection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresSafetyPractice Context triple: [Woodworking, requiresSafetyPractice, eye protection]
-
A.
safetyRequirement
chosen
Indicates that one entity specifies or imposes conditions, standards, or measures necessary to ensure the safety of another entity or activity.
-
B.
requiresPractice
Indicates that performing or mastering one entity depends on engaging in repeated practice or training involving another entity.
-
C.
requiresCautionIn
Indicates that engaging with or operating within the referenced context, situation, or environment demands heightened care, attention, or precaution.
-
D.
hasSafetyRegulationCompliance
Indicates that an entity adheres to, satisfies, or is in conformity with specified safety regulations or standards.
-
E.
supportsSafetyChecks
Indicates that an entity provides or enables mechanisms for performing safety checks or validations.
- 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_69ef840c8b2c8190946ae9522774ba51 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: April 27, 2026, 7:26 p.m.