Triple
T5937970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arrow |
E132089
|
entity |
| Predicate | refersToAircraftRole |
P64994
|
FINISHED |
| Object | fighter aircraft |
—
|
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: fighter aircraft | Statement: [Arrow, refersToAircraftRole, fighter aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToAircraftRole Context triple: [Arrow, refersToAircraftRole, fighter aircraft]
-
A.
referredAircraftRole
chosen
Indicates that one aircraft is mentioned or designated in relation to another aircraft’s role, function, or status within a specific context or event.
-
B.
basedAircraftRole
Indicates that an aircraft is regularly stationed at a particular location in a specified operational role or function.
-
C.
primaryAircraftRole
Indicates the main operational function or mission type an aircraft is primarily designed or used to perform.
-
D.
usedOnAircraftRole
Indicates that something is employed or applied in the context of a specific role or function on an aircraft.
-
E.
aircraftRoleSupported
Indicates that a given role or function is supported or enabled for a particular aircraft.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c03f26f51881908cc253fe5775a1fc |
completed | March 22, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69c03355caf08190b960563a1aed23f9 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 4:01 p.m.