Triple
T8418378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speed Stick Antiperspirant |
E198784
|
entity |
| Predicate | odorControl |
P82083
|
FINISHED |
| Object | underarm body odor |
—
|
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: underarm body odor | Statement: [Speed Stick Antiperspirant, odorControl, underarm body odor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: odorControl Context triple: [Speed Stick Antiperspirant, odorControl, underarm body odor]
-
A.
odor
Indicates that one entity emits, possesses, or is characterized by a particular smell detectable by another entity.
-
B.
interactionWithInsects
Indicates a relationship where an entity engages in some form of contact, behavior, or exchange involving insects.
-
C.
notablePest
Indicates that an entity is recognized as a significant or impactful pest, typically causing notable harm, damage, or nuisance.
-
D.
odorResponse
Indicates a relationship where an entity exhibits a measurable reaction or change in behavior, physiology, or activity in response to an odor stimulus.
-
E.
sporeResistance
Indicates the degree to which an entity can withstand or remain unaffected by spores or spore-related effects.
- 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84c7d6e48190a2bbde89c5d42af6 |
completed | March 31, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69cb70d70ea081909c3dc1bd2ec14f85 |
completed | March 31, 2026, 6:59 a.m. |
| PDg | Predicate description generation | batch_69cb77690720819099de1e22b84a9563 |
completed | March 31, 2026, 7:27 a.m. |
Created at: March 30, 2026, 6:06 p.m.