Triple
T25858963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mossie |
E651429
|
entity |
| Predicate | aircraftVariantOf |
P150446
|
FINISHED |
| Object | de Havilland Mosquito |
—
|
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: de Havilland Mosquito | Statement: [Mossie, aircraftVariantOf, de Havilland Mosquito]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftVariantOf Context triple: [Mossie, aircraftVariantOf, de Havilland Mosquito]
-
A.
specificCarrierAircraftVariant
Indicates that one aircraft variant is a specific version designed or adapted for carrier-based operations of another, more general aircraft variant.
-
B.
airForceVariant
Indicates that one entity is a version or model of something specifically adapted for use by an air force.
-
C.
subjectAircraftNotableVariant
chosen
Indicates that the subject aircraft has a notable or significant variant related to it.
-
D.
usesAircraftVariant
Indicates that one entity operates or employs a specific variant or version of an aircraft.
-
E.
isHelicopterVariantOf
Indicates that one helicopter model is a modified or derived version of another helicopter model.
- 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_69e7ab3a199c81909227cb964cacfe24 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f603bb02288190b40cedbed5b9651d |
completed | May 2, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69f602d07590819085ac34b189613104 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 22, 2026, 8:04 a.m.