Triple
T23213780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Project Airseeker |
E580674
|
entity |
| Predicate | platformCrew |
P21064
|
FINISHED |
| Object | aircrew and intelligence specialists |
—
|
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: aircrew and intelligence specialists | Statement: [Project Airseeker, platformCrew, aircrew and intelligence specialists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformCrew Context triple: [Project Airseeker, platformCrew, aircrew and intelligence specialists]
-
A.
commandCrew
Indicates that one entity holds command authority over the crew associated with another entity.
-
B.
crewType
chosen
Indicates the specific role or category of crew associated with an entity, such as the type of personnel assigned to operate or support it.
-
C.
crew
Indicates that one entity serves as the group of people who operate, staff, or work on another entity (such as a vehicle, vessel, or production).
-
D.
coCrewMember
Indicates that two or more individuals serve together as members of the same crew on a shared mission, vehicle, or operation.
-
E.
featureCrew
Indicates that a particular crew member is highlighted or designated as a featured participant within a crew-related context.
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f19162c77c8190ba29c59ea9695316 |
completed | April 29, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:07 p.m.