Triple
T38152495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BAE Systems Hawk T2 |
E952791
|
entity |
| Predicate | isSubvariantOf |
P15288
|
FINISHED |
| Object | BAE Systems Hawk trainer family |
—
|
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: BAE Systems Hawk trainer family | Statement: [BAE Systems Hawk T2, isSubvariantOf, BAE Systems Hawk trainer family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSubvariantOf Context triple: [BAE Systems Hawk T2, isSubvariantOf, BAE Systems Hawk trainer family]
-
A.
isShortenedVariantOf
Indicates that one form of an expression is a shortened or abbreviated version of another, longer form.
-
B.
denotesVariantOf
Indicates that one entity is a variant or alternative form of another, typically sharing core identity or function with some differences.
-
C.
rulesVariantOf
Indicates that one set of rules is a modified or alternative version derived from another set of rules.
-
D.
isVersionOf
chosen
Indicates that one entity is a particular version, edition, or variant derived from another entity.
-
E.
isRobustVariantOf
Indicates that one entity is a strengthened, more resilient, or more general form of another, preserving the original’s core properties while improving its robustness.
- 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_69f76f0a67f4819080c492f61d688fcc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.