Triple
T10005250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Escape (fragrance) |
E198224
|
entity |
| Predicate | topNotes |
P39617
|
FINISHED |
| Object | coriander |
—
|
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: coriander | Statement: [Escape (fragrance), topNotes, coriander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topNotes Context triple: [Escape (fragrance), topNotes, coriander]
-
A.
topNote
chosen
Indicates that one entity serves as the primary or highest-level note associated with another entity.
-
B.
marksTones
Indicates that one entity applies or denotes tonal markings or distinctions on another entity, such as in language or notation.
-
C.
notableChorus
Indicates that an entity is recognized for having a particularly prominent or distinguished chorus section.
-
D.
baseNote
Indicates that one entity serves as the fundamental or reference note upon which another musical element (such as a chord, scale, or interval) is built or defined.
-
E.
topLevel
Indicates that an entity occupies the highest or outermost level in a hierarchy, structure, or organizational arrangement, with no parent above it.
- 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.