Triple
T37661569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Small End Islands |
E937727
|
entity |
| Predicate | supportsRedstone |
P100824
|
FINISHED |
| Object | Yes, on End Stone |
—
|
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: Yes, on End Stone | Statement: [Small End Islands, supportsRedstone, Yes, on End Stone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsRedstone Context triple: [Small End Islands, supportsRedstone, Yes, on End Stone]
-
A.
hasRedstoneInteraction
chosen
Indicates that there is some form of interaction or effect between the subject and a redstone-related mechanism or signal.
-
B.
supportsBlock
Indicates that one entity provides structural or functional backing that upholds or stabilizes another entity or block.
-
C.
supportsRedo
Indicates that an action, operation, or system can be reapplied or restored after being undone (i.e., it has redo capability).
-
D.
supportsRedundancy
Indicates that one entity provides or enables backup or failover capabilities for another to ensure continued operation if a primary component fails.
-
E.
supportsBlockchain
Indicates that one entity provides compatibility with, infrastructure for, or endorsement of blockchain technology used by another entity.
- 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_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.