Triple
T3300562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Economy Class |
E69319
|
entity |
| Predicate | typicalSeatWidthRange |
P19786
|
FINISHED |
| Object | 16–18 inches |
—
|
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: 16–18 inches | Statement: [Economy Class, typicalSeatWidthRange, 16–18 inches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSeatWidthRange Context triple: [Economy Class, typicalSeatWidthRange, 16–18 inches]
-
A.
typicalWidth
chosen
Indicates the usual or characteristic width associated with an entity, as opposed to an exact or measured width in a specific instance.
-
B.
seatingConfiguration
Indicates how seats are arranged or organized relative to each other in a given context.
-
C.
seatStructure
Indicates that one entity serves as the structural or physical seating component or arrangement associated with another entity.
-
D.
hasSeating
Indicates that one entity provides or contains seating capacity or seating arrangements for another entity.
-
E.
typicalPanelSize
Indicates the usual or standard dimensions associated with a given panel.
- 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_69ad859e529c8190a404273f53cb487d |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0a66fcc819093931fe7a6507723 |
completed | March 8, 2026, 5:23 p.m. |
| PD | Predicate disambiguation | batch_69ada42625308190be257f16a623a410 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.