Triple
T28978447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Marvels |
E734480
|
entity |
| Predicate | featuresPowerSwapping |
P198382
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [The Marvels, featuresPowerSwapping, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresPowerSwapping Context triple: [The Marvels, featuresPowerSwapping, true]
-
A.
powersFeature
Indicates that one entity provides the underlying functionality or capability that enables a particular feature of another entity.
-
B.
powerInterface
Indicates that one entity serves as a power-providing interface or connection point for another entity, enabling the transfer or supply of electrical power.
-
C.
featuresPowerUp
Indicates that one entity includes, provides, or incorporates a power-up as part of its content or functionality.
-
D.
powerSwitchType
Indicates the specific kind or configuration of power switch associated with or used by an entity.
-
E.
powerManagementFeatures
Indicates that one entity provides, supports, or is associated with capabilities for controlling, optimizing, or conserving the power usage of another entity.
- F. None of above. chosen
Provenance (4 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_69f05b0d1e7c819092baab93d3fe277e |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fee0b2da3c8190a3519d0564f2f32d |
completed | May 9, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69fee05b315c819081dfcbfb15273487 |
completed | May 9, 2026, 7:20 a.m. |
| PDg | Predicate description generation | batch_69fee0b03a0c81909117dc5915d77295 |
completed | May 9, 2026, 7:22 a.m. |
Created at: April 28, 2026, 9:10 a.m.