Triple
T129998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bay of Pigs Invasion |
E2632
|
entity |
| Predicate | airComponent |
P2541
|
FINISHED |
| Object | CIA-operated B-26 bombers |
—
|
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: CIA-operated B-26 bombers | Statement: [Bay of Pigs Invasion, airComponent, CIA-operated B-26 bombers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airComponent Context triple: [Bay of Pigs Invasion, airComponent, CIA-operated B-26 bombers]
-
A.
cockpitType
Indicates the specific configuration or style of cockpit associated with an entity (e.g., vehicle or aircraft).
-
B.
aircraft
chosen
Indicates that an entity is an aircraft or functions in the role of an aircraft in the described context.
-
C.
landingGear
Indicates that an entity’s landing gear is present, deployed, or otherwise involved in a landing-related state or action relative to another entity or context.
-
D.
airfieldName
Indicates the name assigned to an airfield in the relationship.
-
E.
aircraftConfiguration
Indicates the specific arrangement or setup of an aircraft’s components, systems, or features for a given purpose or operating condition.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257845c548190bfb49409988d1c57 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a2564da96c8190aa8204de25229c15 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.