Triple
T27974408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | helium–neon laser |
E706446
|
entity |
| Predicate | safetyClass |
P54985
|
FINISHED |
| Object | often Class II |
—
|
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: often Class II | Statement: [helium–neon laser, safetyClass, often Class II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safetyClass Context triple: [helium–neon laser, safetyClass, often Class II]
-
A.
safetyCategory
chosen
Indicates the classification of something according to its level or type of safety.
-
B.
safetyProfile
Indicates the overall level and characteristics of risk or harm associated with something, typically summarizing how safe it is under specified conditions.
-
C.
safetyRatingHighlight
Indicates that an entity’s safety rating is emphasized or specially marked as noteworthy compared to others.
-
D.
safetyContext
Indicates the circumstances, conditions, or environment that affect how safe an action, object, or situation is.
-
E.
safetyLegacy
Indicates that an entity’s current safety status, practices, or conditions are influenced or determined by past safety decisions, standards, or incidents.
- 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_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 7:40 p.m.