Triple
T10005227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Obsession (fragrance) |
E198223
|
entity |
| Predicate | initialConcentration |
P39616
|
FINISHED |
| Object | eau de parfum |
—
|
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: eau de parfum | Statement: [Obsession (fragrance), initialConcentration, eau de parfum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialConcentration Context triple: [Obsession (fragrance), initialConcentration, eau de parfum]
-
A.
concentration
chosen
Indicates the degree to which a substance or entity is present within a given medium, mixture, or space.
-
B.
concentrationComponent
Indicates that one entity is a constituent or ingredient whose amount contributes to the overall concentration of another entity (such as a mixture, solution, or sample).
-
C.
initialStatus
Indicates the original or starting state assigned to an entity before any changes or updates occur.
-
D.
initialNumberOfChemicalsListed
Indicates the original count of distinct chemicals that were recorded or specified at the start of a process or listing.
-
E.
concentrationClass
Indicates the classification of an entity based on the level or range of its concentration.
- 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_69ca830fcca48190bbbd9b20c233835f |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd157d9c8190b863e4264f9a48b1 |
completed | April 2, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69cd1da2cf9081908a6c0eb5247d0bc2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:51 p.m.