Triple
T32562874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | QWERTY keyboard layout |
E832274
|
entity |
| Predicate | hasKeyRow |
P25794
|
FINISHED |
| Object | top letter row |
—
|
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: top letter row | Statement: [QWERTY keyboard layout, hasKeyRow, top letter row]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyRow Context triple: [QWERTY keyboard layout, hasKeyRow, top letter row]
-
A.
hasRow
chosen
Indicates that one entity contains, includes, or is associated with a specific row within a structured arrangement such as a table, grid, or dataset.
-
B.
hasKeyCol
Indicates that one entity serves as the key column (or set of key columns) used to uniquely identify or index records in another entity, such as a table or dataset.
-
C.
hasKeyElement
Indicates that one entity contains or depends on another entity that serves as a primary or essential component.
-
D.
hasKeyField
Indicates that one entity possesses or defines a primary identifying field used as a key in relation to another entity.
-
E.
hasKeyPosition
Indicates that an entity holds an important or central role or position within a structure, system, or organization.
- 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_69f34926b9848190ace47d2dd0a0de7c |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 1, 2026, 1:03 a.m.