Triple
T34827569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annual Rose Festival |
E1003970
|
entity |
| Predicate | hasProductFocus |
P3585
|
FINISHED |
| Object | rose oil |
—
|
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: rose oil | Statement: [Annual Rose Festival, hasProductFocus, rose oil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProductFocus Context triple: [Annual Rose Festival, hasProductFocus, rose oil]
-
A.
hasMarketFocus
Indicates that an entity concentrates its business activities, products, or services on a particular market or customer segment.
-
B.
hasProduct
chosen
Indicates that an entity possesses, offers, or is associated with a particular product.
-
C.
hasReviewFocus
Indicates that a review specifically concentrates on or emphasizes a particular aspect, feature, or component of the subject.
-
D.
hasProgramFocus
Indicates that an entity (such as a program or initiative) is oriented around or primarily concerned with a particular thematic area, topic, or objective.
-
E.
hasCoverageFocus
Indicates that one entity’s coverage, attention, or analysis is specifically focused on or directed toward another entity.
- 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_69f76db7d1b4819093bd4912d80d845d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a032b2285ac81908826f311a222c749 |
completed | May 12, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_6a032929b8b88190bf7d14d789b38aeb |
completed | May 12, 2026, 1:20 p.m. |
Created at: May 3, 2026, 4 p.m.