Triple
T38012778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UN 1671 |
E948409
|
entity |
| Predicate | hasHazardClassName |
P189858
|
FINISHED |
| Object | Toxic substances |
—
|
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: Toxic substances | Statement: [UN 1671, hasHazardClassName, Toxic substances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHazardClassName Context triple: [UN 1671, hasHazardClassName, Toxic substances]
-
A.
hasHazardClass
chosen
Indicates that an entity is assigned to a specific hazard classification category, typically reflecting its risk or danger level under a defined safety or regulatory system.
-
B.
hasHazardCharacteristic
Indicates that an entity possesses a specific hazardous property, condition, or risk-related characteristic.
-
C.
hasHazardLevel
Indicates that an entity is associated with a specified degree or category of risk or danger.
-
D.
hasHazardRelation
Indicates a relationship where one entity poses, contributes to, or is associated with a potential hazard or risk affecting another entity.
-
E.
isHazard
Indicates that something poses a potential risk, danger, or harmful condition to people, property, or the environment.
- 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_69f76efb4b10819092c8c2ba28ac06a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:20 p.m.