Triple
T22330885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MCAS |
E552017
|
entity |
| Predicate | softwareUpdate |
P147779
|
FINISHED |
| Object | Boeing 737 MAX return-to-service modifications |
—
|
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: Boeing 737 MAX return-to-service modifications | Statement: [MCAS, softwareUpdate, Boeing 737 MAX return-to-service modifications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softwareUpdate Context triple: [MCAS, softwareUpdate, Boeing 737 MAX return-to-service modifications]
-
A.
softwareUpdateModel
Indicates that one entity serves as the model, specification, or type definition used to perform or describe a software update on another entity.
-
B.
softwareUpdatable
Indicates that a software system or component can be modified or upgraded after deployment, typically through patches, updates, or new versions.
-
C.
unveiledSoftwareUpdate
Indicates that an entity has publicly revealed or announced a new or updated version of a software product.
-
D.
driverSoftware
Indicates that one entity is software that controls or interfaces with the hardware or system functionality of another entity.
-
E.
supportsOneClickUpdates
Indicates that an entity enables or is compatible with performing updates through a streamlined, single-action (one-click) process.
- F. None of above. chosen
Provenance (4 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1577a9c348190b8662142afa832be |
completed | April 29, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e73004d9e88190bb862319a5aea06b |
completed | April 21, 2026, 8:06 a.m. |
| PDg | Predicate description generation | batch_69e7342ce08c8190bc0a7085f4a952e7 |
completed | April 21, 2026, 8:24 a.m. |
Created at: April 16, 2026, 8:43 p.m.