Triple
T4118297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Atlantic GlobalFlyer |
E90346
|
entity |
| Predicate | notableFlightStartDate |
P28082
|
FINISHED |
| Object | 2005-02-28 |
—
|
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: 2005-02-28 | Statement: [Virgin Atlantic GlobalFlyer, notableFlightStartDate, 2005-02-28]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableFlightStartDate Context triple: [Virgin Atlantic GlobalFlyer, notableFlightStartDate, 2005-02-28]
-
A.
firstFlownAt
chosen
Indicates the date or time at which something (typically an aircraft or spacecraft) was first flown.
-
B.
airlineCommencedOperations
Indicates that an airline began its official flight operations or commercial services on a specific date or at a specific time.
-
C.
airlineOperationsStartYear
Indicates the calendar year in which an airline began its operational activities or commercial service.
-
D.
finalCommercialFlightDate
Indicates the calendar date on which an entity’s last commercial flight operation took place.
-
E.
winningFlightDate
Indicates the date on which the associated flight is determined to be the winning or selected one among a set of candidate flights.
- 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_69aed95c080881908125e30c5dcdc6f8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0246e40081908ad6741a830ca68e |
completed | March 9, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69af01867698819098e4144634b2ec4f |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:41 p.m.