Triple
T37664862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basalt Deltas |
E937797
|
entity |
| Predicate | hasGenerationFeature |
P115058
|
FINISHED |
| Object | ore generation |
—
|
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: ore generation | Statement: [Basalt Deltas, hasGenerationFeature, ore generation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGenerationFeature Context triple: [Basalt Deltas, hasGenerationFeature, ore generation]
-
A.
hasReleaseGeneration
Indicates that one entity is associated with a particular release generation or version cycle of another entity.
-
B.
hasGenerationCode
Indicates that an entity is associated with a specific generation code that identifies its generational category or version.
-
C.
secondGenerationHasFeature
Indicates that an entity’s second generation (e.g., offspring or derived items two steps removed) possesses a specified feature or characteristic.
-
D.
hasFeature
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
E.
hasTypeOfGeneration
chosen
Indicates that one entity is characterized by or associated with a particular kind or method of generation.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe5ec9028081909ae3d6fbe2f4cbbc |
completed | May 8, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69fe5e1d715881909fc516fafc707644 |
completed | May 8, 2026, 10:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.