Triple
T9101245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pegas Fly |
E218159
|
entity |
| Predicate | fleetType |
P6198
|
FINISHED |
| Object | Boeing 737 |
E22402
|
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: Boeing 737 | Statement: [Pegas Fly, fleetType, Boeing 737]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boeing 737 Context triple: [Pegas Fly, fleetType, Boeing 737]
-
A.
Boeing 737
chosen
The Boeing 737 is a widely used narrow-body commercial jet airliner known for being one of the best-selling passenger aircraft in aviation history.
-
B.
Boeing 737-800
The Boeing 737-800 is a widely used narrow-body commercial jet airliner known for short- to medium-haul flights and high fuel efficiency within the 737 Next Generation family.
-
C.
Boeing 737-700
The Boeing 737-700 is a member of Boeing's Next Generation 737 family, a twin-engine narrow-body jet airliner widely used for short- to medium-haul commercial flights.
-
D.
Boeing 737-900ER
The Boeing 737-900ER is an extended-range variant of the 737-900, designed as a high-capacity, single-aisle jetliner for medium-haul commercial flights.
-
E.
Boeing 757
The Boeing 757 is a mid-size, narrow-body twin-engine jet airliner widely used for short- to medium- and some long-haul routes, known for its strong performance and versatility.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc971435d08190b5007ed44ac0a364 |
completed | April 1, 2026, 3:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d030201a048190a3a1166d23c5ae67 |
completed | April 3, 2026, 9:24 p.m. |
Created at: March 30, 2026, 7:15 p.m.