Triple
T19987525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NES-101 |
E493971
|
entity |
| Predicate | cartridgeInsertionMethod |
P135939
|
FINISHED |
| Object | vertical top-loading |
—
|
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: vertical top-loading | Statement: [NES-101, cartridgeInsertionMethod, vertical top-loading]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cartridgeInsertionMethod Context triple: [NES-101, cartridgeInsertionMethod, vertical top-loading]
-
A.
cartridgeInsertion
chosen
Indicates that one entity is being inserted or placed into another entity in the form of a cartridge.
-
B.
requiresCartridgeSlotOf
Indicates that one entity needs to use or be connected to the cartridge slot provided by another entity in order to function or be compatible.
-
C.
cartridge
Indicates that one entity is a cartridge associated with, contained in, or used by another entity.
-
D.
intendedCartridgeStandard
Indicates that an item is designed to be used with, or conform to, a particular cartridge standard.
-
E.
cardSlots
Indicates a relationship where specific positions or slots are allocated or available for holding cards.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fdd1a5c8190af756632aac38bf4 |
completed | April 20, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69e537fd311881908448f2aea8b4812e |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:29 p.m.