Triple
T8433719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Infinity Stones |
E199174
|
entity |
| Predicate | MCUUsage |
P2529
|
FINISHED |
| Object | used to erase half of all life in the universe |
—
|
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: used to erase half of all life in the universe | Statement: [Infinity Stones, MCUUsage, used to erase half of all life in the universe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MCUUsage Context triple: [Infinity Stones, MCUUsage, used to erase half of all life in the universe]
-
A.
usageType
chosen
Indicates the specific manner, purpose, or context in which something is used or intended to be used.
-
B.
platformUsage
Indicates how an entity uses, engages with, or relies on a particular platform for its activities or services.
-
C.
hasMCR
Indicates a relationship where an entity is associated with, or possesses, a specific MCR (e.g., a defined minimum capital requirement or similarly named regulatory/technical measure).
-
D.
usesToolType
Indicates that an entity performs an action or fulfills a role by employing a specific type or category of tool.
-
E.
canUse
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe30fba4081908bfdef3faf5baceb |
completed | March 31, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69cbd0ec200c8190b0299e2b0b4bdcc2 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:07 p.m.