Triple
T24652701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rochow process |
E610296
|
entity |
| Predicate | downstreamProduct |
P83279
|
FINISHED |
| Object | polydimethylsiloxane |
—
|
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: polydimethylsiloxane | Statement: [Rochow process, downstreamProduct, polydimethylsiloxane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: downstreamProduct Context triple: [Rochow process, downstreamProduct, polydimethylsiloxane]
-
A.
byProduct
chosen
Indicates that one entity is produced incidentally or as a secondary result of a process, activity, or creation involving another entity.
-
B.
laterProductType
Indicates that one product type occurs or is introduced after another product type in time or sequence.
-
C.
providedProduct
Indicates that one entity has supplied or made available a particular product to another entity.
-
D.
productWith
Indicates a relationship where one entity is associated with, contains, or is offered together with another entity as a product.
-
E.
productFor
Indicates that one entity is intended to be used by, with, or in relation to another entity as its product or offering.
- 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_69e2c4d350a481909170482bc2ce6af9 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f422aee0408190899efe7e24ef2b40 |
completed | May 1, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f420e92cc88190a803aecdae78a051 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 2:34 a.m.