Triple
T7357690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Residence (on selected A380 aircraft) |
E169666
|
entity |
| Predicate | components |
P14071
|
FINISHED |
| Object | living room |
—
|
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: living room | Statement: [The Residence (on selected A380 aircraft), components, living room]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: components Context triple: [The Residence (on selected A380 aircraft), components, living room]
-
A.
component3
Indicates that one entity is the third component or sub-part within a larger composite structure or system involving another entity.
-
B.
component1
chosen
Indicates that one entity functions as a constituent or part of another entity within a larger whole.
-
C.
componentPractice
Indicates that one entity is a specific practice, method, or procedure that functions as a component or sub-practice within another, broader practice or process.
-
D.
componentFrom
Indicates that one entity is derived from, produced by, or originates as a component of another entity.
-
E.
componentAct
Indicates that an action or behavior is performed by a component as part of a larger system or process.
- 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_69c68a59f2288190877ca15c19b1e822 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f26d6d6081909c7272a9ccae0d97 |
completed | March 27, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69c6f02d36108190bcb34a95e6a30bd7 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:06 p.m.