Triple
T2151110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winston (cigarette) |
E47181
|
entity |
| Predicate | hasHealthEffect |
P19730
|
FINISHED |
| Object | causes lung cancer |
—
|
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: causes lung cancer | Statement: [Winston (cigarette), hasHealthEffect, causes lung cancer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHealthEffect Context triple: [Winston (cigarette), hasHealthEffect, causes lung cancer]
-
A.
healthEffect
chosen
Indicates the impact or consequence that one entity has on the health or well-being of another.
-
B.
involvedPhysicalEffect
Indicates that one entity participates in causing, experiencing, or mediating a physical effect on another entity or the environment.
-
C.
notableEffect
Indicates that one entity has a significant impact, consequence, or influence on another entity or situation.
-
D.
foodEffect
Indicates how consuming a particular food influences or changes another entity, such as an organism, condition, or process.
-
E.
hasCommonAdverseEffect
Indicates that two or more entities share at least one adverse effect that occurs in response to them.
- 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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe4747a0819080e2234f3ea8995f |
completed | March 7, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69abbd9a60648190b20b116be5c7ad98 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.