Triple
T35843533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City of Kandor |
E1036149
|
entity |
| Predicate | enemyResponsibleForMiniaturization |
P107379
|
FINISHED |
| Object | Brainiac |
—
|
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: Brainiac | Statement: [City of Kandor, enemyResponsibleForMiniaturization, Brainiac]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enemyResponsibleForMiniaturization Context triple: [City of Kandor, enemyResponsibleForMiniaturization, Brainiac]
-
A.
miniaturizedBy
chosen
Indicates that an entity has been made smaller in size or scale by another entity or process.
-
B.
miniaturizedIn
Indicates that one entity exists as a smaller-scale or reduced-size version within or relative to another entity.
-
C.
dieShrinkOf
Indicates that one entity is a smaller, more advanced manufacturing process node derived from the other entity’s larger, earlier process node.
-
D.
dieShrinkOf
Indicates that one entity is a smaller, more advanced manufacturing process node derived from another, larger process node.
-
E.
minimizedBy
Indicates that one entity serves to reduce, lessen, or make as small as possible the value, effect, or impact of 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_69f76e1a29e8819088280f26096aeb55 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3883d48190b05e3d2da7a017ae |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.