Triple
T2132325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIAI-Marchetti SF.260 |
E46567
|
entity |
| Predicate | variant |
P4680
|
FINISHED |
| Object | SF.260TP |
E237926
|
NE 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: SF.260TP | Statement: [SIAI-Marchetti SF.260, variant, SF.260TP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SF.260TP Context triple: [SIAI-Marchetti SF.260, variant, SF.260TP]
-
A.
SF.260TP
chosen
The SF.260TP is a turboprop-powered variant of the SIAI-Marchetti SF.260, used primarily as a military trainer and light attack aircraft.
-
B.
SF.260D
The SF.260D is an upgraded variant of the Italian SIAI-Marchetti SF.260 light aircraft, used primarily for military training and aerobatic roles.
-
C.
SF.260C
The SF.260C is a later production version of the Italian SIAI-Marchetti SF.260 light aircraft, used primarily for military training and aerobatics.
-
D.
SF.260 Warrior
The SF.260 Warrior is a military-oriented variant of the Italian-designed SIAI-Marchetti SF.260, used primarily for training and light attack roles.
-
E.
FR-26
FR-26 is the ISO 3166-2 code designating the Drôme department in southeastern France.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88a1626548190ae59a5028c3baa8e |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbb7b13ac819094d43159fff984cf |
completed | March 7, 2026, 5:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae7ef2dda08190b55919f0df935a6d |
completed | March 9, 2026, 8:04 a.m. |
Created at: March 4, 2026, 7:44 p.m.