Triple
T31704748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sting Ray torpedo |
E809147
|
entity |
| Predicate | launchAircraftExample |
P176354
|
FINISHED |
| Object | Westland Lynx helicopter |
—
|
NE NERFINISHED |
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: Westland Lynx helicopter | Statement: [Sting Ray torpedo, launchAircraftExample, Westland Lynx helicopter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: launchAircraftExample Context triple: [Sting Ray torpedo, launchAircraftExample, Westland Lynx helicopter]
-
A.
launchAircraftRole
Indicates the role or function an entity has in initiating or carrying out the launch of an aircraft.
-
B.
launchedAircraftIn
Indicates that an entity initiated the takeoff or deployment of an aircraft within a specified location or context.
-
C.
launchAirfield
Indicates that an entity initiates or conducts the launch of an aircraft or aerial operation from a specific airfield.
-
D.
aircraftCommanded
Indicates that one entity serves as the commanding officer or leader in charge of operating, directing, or overseeing the other entity, which is an aircraft.
-
E.
landingCapability
Indicates the ability or suitability of an entity (e.g., a vehicle or system) to perform a landing under specified conditions.
- 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_69f348de914081909fc8edff56f34dbe |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6e02ba6b881908dfafc52d3b75f1c |
completed | May 3, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69f6de09c2f481909f8b2545d3208c9f |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6e029f0f88190b1f88d82a4a2cabd |
completed | May 3, 2026, 5:42 a.m. |
Created at: April 30, 2026, 11:13 p.m.