Triple
T7303335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AC-8 |
E167911
|
entity |
| Predicate | smokeManagementPurpose |
P76097
|
FINISHED |
| Object | keep exhaust away from crew in tunnels and snow sheds |
—
|
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: keep exhaust away from crew in tunnels and snow sheds | Statement: [AC-8, smokeManagementPurpose, keep exhaust away from crew in tunnels and snow sheds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: smokeManagementPurpose Context triple: [AC-8, smokeManagementPurpose, keep exhaust away from crew in tunnels and snow sheds]
-
A.
smokeUse
Indicates that an entity uses or consumes tobacco or other substances by smoking.
-
B.
canBeSmoked
Indicates that something is suitable or able to be consumed by smoking.
-
C.
smokeSystem
Indicates that an entity is equipped with or associated with a smoke-generating system (e.g., for signaling, testing, or special effects).
-
D.
smokingMaterial
Indicates that one entity is a material or substance used for smoking by another entity.
-
E.
usesTobaccoType
Indicates that an entity consumes or makes use of a specified type or form of tobacco.
- F. None of above. chosen
Provenance (4 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_69c6888c820881909fc68f689fe1c251 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6ebb2261c8190ae9095c8e110b528 |
completed | March 27, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69c6e76e67d88190bd3ca6864f45845a |
completed | March 27, 2026, 8:24 p.m. |
| PDg | Predicate description generation | batch_69c6eb2d4c0c8190b4cc6fdfdb7f4827 |
completed | March 27, 2026, 8:40 p.m. |
Created at: March 27, 2026, 3:01 p.m.