Triple
T3203768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Harcourt Refining Company |
E67110
|
entity |
| Predicate | feedstock |
P5629
|
FINISHED |
| Object | crude 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: crude oil | Statement: [Port Harcourt Refining Company, feedstock, crude oil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feedstock Context triple: [Port Harcourt Refining Company, feedstock, crude oil]
-
A.
feedSystem
Indicates that one entity supplies or provides input, resources, or data into another entity or system for its operation or processing.
-
B.
primaryFeedstock
chosen
Indicates that one entity serves as the main raw material or input used to produce, process, or operate another entity.
-
C.
dataFeeds
Indicates that one entity supplies or streams data to another entity for use, processing, or analysis.
-
D.
feedingStructure
Indicates a relationship where one entity serves as the anatomical or mechanical structure used by another entity to obtain or ingest food.
-
E.
feederSystem
Indicates a system or mechanism that supplies or feeds resources, materials, or inputs into another process, component, or structure.
- 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_69ad8589bd988190afa7ed2bdffb7b33 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaa54124c8190a22089ce2eaedab5 |
completed | March 8, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69ad9e078f7c8190813d9fcb4f5071fb |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:07 p.m.