Triple
T28969057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kylos |
E734221
|
entity |
| Predicate | destroyedInBackstoryOf |
P134265
|
FINISHED |
| Object | Drax the Destroyer |
—
|
NE NERFINISHED |
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: Drax the Destroyer | Statement: [Kylos, destroyedInBackstoryOf, Drax the Destroyer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destroyedInBackstoryOf Context triple: [Kylos, destroyedInBackstoryOf, Drax the Destroyer]
-
A.
destroyedInMythBy
Indicates that one entity is said, within a myth or mythological narrative, to have been destroyed by another entity.
-
B.
destroyedFor
Indicates that one entity was ruined, eliminated, or rendered unusable specifically for the benefit, purpose, or objective of another entity.
-
C.
destroyedDuring
Indicates that one entity was destroyed in the course of, or as a consequence of, a specified event or time period.
-
D.
sufferedDestructionOf
Indicates that one entity experienced damage, ruin, or loss as a result of the destruction of another entity.
-
E.
destroyedInText
chosen
Indicates that one entity is described as being destroyed within the content or narrative of a given text.
- 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_69f05b0d1e7c819092baab93d3fe277e |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65c3001908190a21cfe2d25c319eb |
completed | May 2, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:04 a.m.