Triple
T16504985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marine Heavy Helicopter Squadron |
E400902
|
entity |
| Predicate | supportPersonnel |
P81570
|
FINISHED |
| Object | aviation maintenance Marines |
—
|
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: aviation maintenance Marines | Statement: [Marine Heavy Helicopter Squadron, supportPersonnel, aviation maintenance Marines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportPersonnel Context triple: [Marine Heavy Helicopter Squadron, supportPersonnel, aviation maintenance Marines]
-
A.
hasSupportStaff
chosen
Indicates that an entity is associated with one or more staff members who provide assistance or support services to it.
-
B.
servicePerson
Indicates that one entity performs a service or provides assistance to another entity.
-
C.
supportUnits
Indicates that one entity provides assistance, resources, or reinforcement to another entity, often in an operational or functional context.
-
D.
personnel
Indicates that an entity serves as staff or workforce associated with another entity, such as an organization, project, or facility.
-
E.
supportsDepartment
Indicates that one entity provides assistance, resources, or backing to a specific department.
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e51ce1c81909548298f703a7ffa |
completed | April 18, 2026, 7:10 a.m. |
| PD | Predicate disambiguation | batch_69e296902d6c8190884ddb612b8c5b36 |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.