Triple
T7402837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libre (fragrance) |
E170789
|
entity |
| Predicate | concentrationAvailable |
P13910
|
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: [Libre (fragrance), concentrationAvailable, Eau de Parfum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: concentrationAvailable Context triple: [Libre (fragrance), concentrationAvailable, Eau de Parfum]
-
A.
hasConcentration
Indicates that one entity possesses or exhibits a specific level, strength, or density of another substance, property, or attribute.
-
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.
concentration
Indicates the degree to which a substance or entity is present within a given medium, mixture, or space.
-
D.
availableWith
chosen
Indicates that one entity can be obtained, accessed, or used in conjunction with another entity.
-
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_69c68a6010108190925e5284de022660 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f26ea27c8190a55e0e0314b463d8 |
completed | March 27, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69c6f0323b2c819098ab72c33e6d8534 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:10 p.m.