Triple
T11731166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IQOS |
E278898
|
entity |
| Predicate | hasUserAction |
P16860
|
FINISHED |
| Object | inserting tobacco stick into holder |
—
|
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: inserting tobacco stick into holder | Statement: [IQOS, hasUserAction, inserting tobacco stick into holder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUserAction Context triple: [IQOS, hasUserAction, inserting tobacco stick into holder]
-
A.
hasInteraction
Indicates that there is some form of interaction or mutual action occurring between the related entities.
-
B.
hasAct
chosen
Indicates that an entity performs, participates in, or is associated with a specific act or action.
-
C.
hasTimeOfAction
Indicates that an action is associated with a specific point or interval in time when it occurs.
-
D.
hasRecentActivity
Indicates that the subject has performed an action or been involved in an event within a defined recent time period.
-
E.
hasUser
Indicates that an entity is associated with or linked to a specific user.
- 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_69d6aaffec6881908bead509e8621742 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4d94de08190a7184cf26d8cb94e |
completed | April 10, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69d88a7f51248190bf492bd7509b5413 |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.