Triple
T9106139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabian American Oil Company |
E218481
|
entity |
| Predicate | coreResource |
P85738
|
FINISHED |
| Object | Saudi crude oil reserves |
—
|
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: Saudi crude oil reserves | Statement: [Arabian American Oil Company, coreResource, Saudi crude oil reserves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coreResource Context triple: [Arabian American Oil Company, coreResource, Saudi crude oil reserves]
-
A.
targetResource
Indicates that one entity designates another entity as the specific resource or object toward which an action, request, or operation is directed.
-
B.
coreModule
Indicates that something functions as a primary or foundational module within a larger system or structure.
-
C.
resourceExtracted
Indicates that a resource has been obtained or taken from a source entity, typically through an extraction process.
-
D.
strategicResource
chosen
Indicates that the related entity functions as a key asset whose control or availability significantly affects strategic or competitive advantage.
-
E.
primaryResourceType
Indicates the main or predominant type/category of resource associated with an entity or activity.
- 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_69ca83db7448819090d0a5de842ef2ac |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca57286a88190b256d2461c5c0aed |
completed | April 1, 2026, 4:56 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:16 p.m.