Triple
T30503598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Vopak |
E776204
|
entity |
| Predicate | handlesProductType |
P161603
|
FINISHED |
| Object | chemicals |
—
|
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: chemicals | Statement: [Royal Vopak, handlesProductType, chemicals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: handlesProductType Context triple: [Royal Vopak, handlesProductType, chemicals]
-
A.
handlesProductCategory
chosen
Indicates that an entity is responsible for managing or dealing with a specific product category.
-
B.
clearsProductType
Indicates that one entity removes or resets the specified product type association from another entity.
-
C.
productTypeEvaluated
Indicates that an entity’s product type has been assessed or judged according to certain criteria or standards.
-
D.
appliesToProductType
Indicates that something (such as a rule, offer, or condition) is relevant or applicable specifically to a certain type or category of product.
-
E.
hasListedProductType
Indicates that an entity has a product associated with it that is categorized under a specific listed product type.
- 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_69f22498c5d481908aaea89e6fab8280 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 29, 2026, 8:15 p.m.