Triple
T32509133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deviants (MCU) |
E830880
|
entity |
| Predicate | evolutionaryTrait |
P120348
|
FINISHED |
| Object | gain powers of killed Eternals |
—
|
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: gain powers of killed Eternals | Statement: [Deviants (MCU), evolutionaryTrait, gain powers of killed Eternals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evolutionaryTrait Context triple: [Deviants (MCU), evolutionaryTrait, gain powers of killed Eternals]
-
A.
evolutionaryFeature
Indicates a characteristic or trait that has arisen or been shaped through evolutionary processes in an entity.
-
B.
evolutionaryType
Indicates the kind or category of evolutionary relationship or process that applies between entities.
-
C.
evolutionaryRole
Indicates the function or impact an entity has within an evolutionary process, such as how it contributes to adaptation, selection, or lineage change over time.
-
D.
breedingTrait
Indicates that an entity possesses a heritable characteristic that is relevant or targeted in a breeding process or program.
-
E.
developedTrait
chosen
Indicates that an entity has acquired or evolved a particular characteristic, quality, or feature over time.
- 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_69f3492318348190ba37fb6b5f1d67f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1 a.m.